VaynerMedia asked: How might we develop a system that monitors changes in global shoreline and/or other ongoing effects of global warming?

Through brainstorming and feedback sessions, Team Rising Tide decided to focus on how they could engage the public in efforts to reduce carbon emissions. As team member Campbell Weaver said, “How could we encourage people to think about the environment when they’re making everyday decisions in their life?”

The team’s solution, Footprint, is a browser extension that tracks users’ online grocery orders then calculates their carbon footprint. The extension scrapes data from a website’s server, processes it using algorithms, then sends it to online calculators which work out how much carbon dioxide is emitted during an item’s production, packaging, and shipping. The results are displayed as green (low), yellow (medium), or red (high) plant-shaped labels; the design idea was inspired by organic labeling schemes.

Footprint is designed to have a wide reach, said Weaver, “20 percent of your individual footprint comes from your dietary choices and online shopping is growing; it’s an industry that’s going to touch 90 percent of households in a couple of years.”

Team members included Ryan Farr, Master in Computer Science ’19, Campbell Weaver, Master in Computer Science ’19, Wen Guo, Johnson Cornell Tech MBA ’19, and Maximilian Kuester, Master in Operations Research and Information Engineering ’19.

Output asked: How might we use technology to empower people to be musically creative without formal music training?

Team Remuse shares a love of listening to and making music, and believes that musical creativity has a positive impact on society since it can empower people and improve wellbeing; they jumped at Output’s challenge.

The team’s music modification app, Remuse, is inspired by Instagram and Snapchat filters. “Users can input popular songs they find on their iTunes or that they download. Then they can apply simple filters to make it sound higher-pitched, or make the voice sound funky, or add nice backing,” said team member Dhruv Jain. The app scans MP3 files and renders them editable. Via a sliding window, users can select and alter parts of the waveform.They can also change the pitch and frequency or add noise and distortion.  

Music is a powerful force for social good, said the team, since it can provide emotional support during difficult times and can connect people. By making musical creativity more accessible, Remuse aims to help people express themselves. “If we can get more people to make more music, I think the world will be better for it,” said Jain.

Team members included Kelly Sun, Technion-Cornell Dual Master’s Degrees in Connective Media ’19, Benjamin Hwang, Master in Operations Research and Information Engineering ’19, Dhruv Jain, Johnson Cornell Tech MBA ’19, and Mike Chen, Master in Computer Science ’19

The Anti-Defamation League (ADL) asked: How might we create tools or services to support likely and actual targets of cyberhate and cyberharassment?

ADL’s challenge struck a chord with the members of Team Triggr, all of whom have been affected, either directly or indirectly, by cyberharassment. Through interviews with victims, the team found that reporting incidents of cyberhate can be traumatic. “On a social platform like Twitter, if you want to report toxic messages, you have to complete a survey for every negative message you receive,” said Yixue Wang. Not only is this time-consuming, but it also forces victims to revisit the harmful material.

The team’s solution is Triggr, an app that scrapes a user’s social media for negative messages and aggregates them, allowing victims to report in bulk. Triggr also contains links to mental health and legal resources.

Team members included Mark O’Looney, Johnson Cornell Tech MBA ’19, Meera Nanda, Technion-Cornell Dual Master’s Degrees in Connective Media ’19, Michael Barron, Master in Computer Science ’19, and Yixue Wang, Technion-Cornell Dual Master’s Degrees in Connective Media ’19.

All three teams agreed that working with peers and faculty in Cornell Tech’s open, collaborative environment was key to the success of their projects. “It is so multidisciplinary,” said Team Rising Tide’s Ryan Farr. “For civic and social tech, we have some really great professors in the faculty. It’s something that I really haven’t seen at any other university.”

The post Positive Impact: Students Build Tech for Societal Good appeared first on Cornell Tech.

Memorial Sloan Kettering Cancer Center asked: How might we free clinicians from computer workstations, allowing them to focus directly on their patients during clinical encounters?

Eshann Toteja, Master in Computer Science ’19, said he was inspired to take on this challenge in part by his and his teammates’ personal experiences in clinical settings: “As patients at hospitals, our whole team has felt ignored or unimportant at some point in the exam room.”

In addition to improving patients’ experiences, Toteja said their goal was to stay “valuable and true to the biggest problems we saw providers facing in exam rooms.”

The team started by learning as much as they could from as many people as possible in the healthcare industry about the problems providers faced in the exam room. They also researched the kinds of solutions already being explored to address those problems.

“We did quite a few on-site days with Memorial Sloan Kettering,” said Skyler Erickson, Master in Computer Science ’19, “and we were working with physicians there and observing patient encounters and really trying to dig into, ‘Where is the computer workstation a problem and when does that distract from the patient interaction?’”

For Erickson, one of the key moments was “this realization that it’s not so much about what you do see, it’s equally important what you don’t see.” For example, he said, they never saw a physician pull up exam results during an appointment because doing so via their workstation was too difficult, time-consuming, and distracting. The goal, said Erickson, was to allow doctors to order tests “naturally and seamlessly and in one conversation.”

Ultimately the team, which also included Benjamin Yellin, Technion-Cornell Dual Master’s Degrees in Health Tech ’20, and Kriti Shah, Johnson Cornell Tech MBA ’19, developed an efficient new voice assistant, similar to Alexa or Google Home. With the aid of this tool, providers can easily order a test for a patient by saying, “Order a test for Patient X,” rather than interrupting the conversation to navigate various screens on their computer workstations.

The students credit their faculty advisor, Deborah Estrin, Cornell Tech’s Robert V. Tishman ’37 Founder’s Chair, with providing valuable real-world feedback. Toteja described her as “an immense help, constantly offering up the exact criticism and advice we needed to hear.” Her ties to the healthcare field, he said, “kept her current and connected, making her input extremely valuable.”

“We met with her many, many times to make sure we were on the right track and to pivot when we ran into some roadblocks,” said Yellin.

Microsoft asked: How might we use technology to help people with disabilities perform everyday tasks?

As the team from Cornell Tech began thinking about this question, Nabeel Seedat, Master in Electrical and Computer Engineering ’19, said, “We all had an association of people that we knew that had visual disabilities, and we felt that this was something that, as a team, we were all passionate about.” Based on this experience and with assistance from their advisors at Microsoft, the team from Cornell Tech decided to focus on developing a solution for people with visual impairment.

“We wanted to figure out which specific task is a big problem faced by those with vision impairment,” said Raga Kolli, Johnson Cornell Tech MBA ’19. “After doing research online, we realized that a common theme is social engagement—people with vision impairment face a lot of isolation, and a lack of social interaction causes further anxiety. A lot of what we do today is online and there’s a big information gap online for those with visual impairment vs. sighted users.”

That insight led them to tackle the problem of social media engagement, which poses a particular challenge to people with visual disabilities, given the prevalence of image-based content.

Existing solutions address this problem via screen-reader technologies, including programs which describe images simply and literally. Seedat said they wanted to go further, asking themselves, “How could we combine both the image content and the textual content around the image, in order to create a narrative which would allow people to better engage with the content in the posts?’”

They were inspired to develop a web browser extension for people with visual disabilities to use when browsing social media sites. The browser extension “translates” images surrounded by text into a brief description that captures the post’s meaning, not just its literal content. For example, it would translate a photo of a toddler with chocolate smeared all over her face and the caption, “Enjoying her food!” as something like, “Child making a mess with her food” rather than “Child eating food.” This allows people with impaired vision to better understand and meaningfully interact with posts.

Throughout the product development process, the team benefited from feedback from Estrin, their faculty advisor, who encouraged them to develop “not just purely a technological product but also something that can have an impact on people.”

Kolli said Estrin “really helped us figure out our narrative (and) develop an impactful product that has meaning to our users.” Boning Hou, Master in Computer Science ’19, added that Estrin “helped us narrow down the idea and helped us to think about why we are doing what we are doing so that our product will be more helpful to the people that we are trying to help.”

The team has made enormous strides in just one semester. Hou said they have finished a prototype that can parse web content and translate an image into a complete sentence. For now, it works with websites like Instagram and Pinterest; they are in the process of trying to make it compatible with Facebook as well. “Right now, we are planning to make this project open source,” said Hou, “so that more people can contribute to it and make this have a larger impact.”

The post Cornell Tech Students Pioneer New Insights in Health Tech appeared first on Cornell Tech.

Leading companies and organizations in New York City tasked Cornell Tech students to develop innovative technology solutions to their respective cybersecurity challenges. Interdisciplinary Product Studio teams collaborated throughout the fall semester and demonstrated their final prototype — backed by user research and strategy — to key stakeholders.

Here are three solutions Cornell Tech students built:

Blockchain Banking & Marketing Advisors asked: How might we understand cryptocurrencies to help startups launch initial coin offerings that are compliant, valuable, and relevant to the business and customers needs?

The initial public offering (IPO) process has existed for centuries, but the cryptocurrency counterpart is still in its infancy. Initial Coin Offering (ICO) is an unregulated way of crowd-fundraising using cryptocurrencies. The amount of money raised through ICOs has exploded in recent years, but there is still a lot of distrust in the process.

A team of Cornell Tech masters students worked with Blockchain Banking & Marketing Advisors (BBMA), a firm that helps companies manage the initial coin offering process, to try to improve trust in the ICO process.

Cyrus Ghazanfar, Master in Computer Science ‘19 said, “ICOs aren’t subject to the same laws and regulations as IPOs. IPO buyers usually have a vesting period for the shares so they don’t take advantage of the market. It is pre-regulated. That doesn’t exist in the ICO market.”

Some companies participate in an ICO lock-up period, similar to the traditional IPO lock-up period, to ensure that insiders who purchased the stock before the company went public can’t liquidate their assets right away and, in doing so, destabilize the market. However, Ghazanfar explains that there was no way to ensure that the funds were locked during an ICO lock-up period due to the unregulated nature of it.

The cross-disciplinary team from Cornell Tech built Vestvault, a client-facing user interface that leverages smart contract technology to allow founders and other executives within a company to enter the specifications of the shareholder distribution without needing to code. The smart contract vests the tokens to the specified shareholders over time automatically and without the need for a third party. The information they submit is automatically used to generate and upload a smart contract to the blockchain and all users can transparently view any activity in real time to  ensure the lock-up period is maintained. The funds are instantly released when the lock-up period ends.

“This solution is completely decentralized. You don’t need to trust a third party,” said Ghazanfar, “It is the rule of the code. It is a completely autonomous end-to-end solution.”

The most difficult part of building the technology — which relies on coding languages Solidity and Python — was making sure that the smart contract securely and correctly transfers value between “wallets,” Pooja Kale, Masters in Computer Science ’19 said. In the past, companies have lost millions of dollars because of buggy code, according to Ghazanfar.

The team, which also includes Jim Campbell, Johnson Cornell Tech MBA ‘19, and Kibum “George” Byun, Master of Laws in Law, Technology and Entrepreneurship ‘19, may continue to work on their project after graduation and they have already generated interest from meetups they’ve attended and introductions to industry leaders.

Citigroup asked: How might we realize the benefits of shared data and computational models amongst untrusted parties while maintaining the security and privacy of each party and their data?

Cornell Tech students worked with Citigroup to create a prototype that would address anti-money laundering when financial institutions share bank client transaction data. Although the data is not sold or disclosed between financial institutions, it is used to train a model that all of the institutions can access. As soon as the model is built, the data is erased from the local memory. Their product, datawall, enables institutions to share machine-learning models securely.

They built a privately distributed machine-learning platform, enabling the marketization of data that allows multiple financial institutions to work together to train and use machine-learning models. “Central to this framework is the use of smart contracts that executes payment and compensation transactions between the parties per the terms of the contract for any inferences generated by a party querying the model,” said Peng.

“Through this business model innovation, datawall becomes a platform that enables the monetization of data assets and the creation of an inference-as-a-service marketplace,” Peng said. “In addition to a flexible architecture that allows for easy integration of newer security technologies, datawall includes security features such as data validation to protect against security threats such as data poisoning and breaches.”

“The price [financial institutions] pay to access the data and the payout every time a query is used is based on the amount of data [the firm] contributes and the value of the data,” said Daniel Nissani, Technion-Cornell Dual Master’s Degrees in Connective Media ‘20.

The team, which also includes Anthony Bisulco, Master in Electrical and Computer Engineering ’19 and Wei Duan, Master in Computer Science ’19, plans to continue to work on the project and have already had one venture capital meeting. Datawall would generate revenue as a percentage fee on all transactions.

Roku asked: How might we gain the trust, not just consent, of consumers to use their data for personalizing their ad-viewing experience:

Roku tasked Cornell Tech students with helping consumers feel more comfortable sharing their data with the company. At first, the team had trouble assessing if viewers trusted Roku. But then they realized, “You don’t need to say how much you trust a company, but you will show your trust based upon how much you use the product,” said Sergio Campos, Master of Laws in Law, Technology and Entrepreneurship ’19. The team, advised by Ben Biddle and Michael Gladstone from Roku, decided to create a unique ad experience that provides users with more relevant and valuable ads.

They built KonnActAd. When a viewer sees a product they like during a movie or television show, they press pause and are served with ads for products in the scene and can click to shop directly. The team manually selected the product options and displayed them in a web application written using JavaScript for their minimum viable product. They think that media, product, and service companies would be interested in tagging their products in specific scenes. Eventually, they want to automate the entire process by watermarking products in each scene using computer vision.

“Our theory is that if we give people control of when they engage to see ads and make those ads relevant and personalized, they’ll get more of what they want, our algorithm will get better at giving them what they want, and as a result, trust will be built,” said Ryan Sydnor, Johnson Cornell Tech MBA ‘19.

KonnActAd was different from other products in the clinic because it did not exclusively address technical security. “There was an element of ‘social security.’ If there is a group of people in my living room watching my TV and it personalizes embarrassing ads for me, is that acceptable? No, of course not! That would erode trust,” said Sydnor. “Professor Ristenpart was the first to pick up on this and was happy to dive into both technical and social implications of security. His ability to see multiple perspectives on the problem is something that stood out to me about him.”

The team, which also includes Zhenwei Zhang, Technion-Cornell Dual Master’s Degrees in Connective Media ‘20, and Roger Wang, Master in Computer Science ‘19, may continue to work on the project. Campos says that the interdisciplinary team and collaborative experience taught them all new skills — he even submitted his first line of code to GitHub. Instead of sticking to their individual skill sets, they made all decisions together, taught each other, and provided regular feedback.

The post Cornell Tech Students Build Cybersecurity Tools in Product Studio appeared first on Cornell Tech.

That’s why Zheng is so enthusiastic about Cornell Tech’s Product Studio, where she and a cohort of Parsons School of Design students were placed on teams with Cornell Tech masters students.

A former in-house designer for Guardian Life Insurance, Zheng is aware of the difference between assignments that originate in the classroom and those that come from real challenges in the workplace today. She was delighted when her team was tasked with designing better machine learning interfaces for Google’s customer service centers. Sitting in on meetings directly with Google, hashing out Google’s needs and presenting her team’s ideas — this was exactly the kind of experience Zheng sought.

“I know the difference between making up a problem and a real-world problem,” said Zheng. Design has limitations like budget, timeline, advertising and real-world users. Without those limitations, the lines between art and design can blur. “The more real [projects] get, the more valuable it gets.”

Making ideas visual

Zheng’s role, as the designer on the four-person Cornell Tech Product Studio team, was to distill ideas visually — everything from building presentation slides to iterating prototypes in Adobe Experience Design.

“My job is to simplify, and get the most important ideas out because we don’t have a lot of time,” said Zheng. “If you just present data and a graph, people will forget in seconds.”

A customer service agent manager browses the overall performance of the team from the historical performance tab.

Design is at the core of every iconic product, from Coca-Cola’s bottle to the iPhone. At Cornell Tech this philosophy is put to work, where 15 Parsons School of Design students were embedded in Product Studio teams, embracing the role of design in product development from beginning to end.

“A well-working team does not have a business person, a programmer, a lawyer, and a designer; it has four founders working together to design a product,” said Justin Bakse, assistant professor of interaction design with Parsons School of Design.

“Each member’s background and expertise informs the [design] process,” Bakse said. “Business, legal and technical concerns provide constraints that help guide the designer.”

Designing new measurement

Google challenged Zheng’s team to help the company analyze customer service experience. In the past, Zheng explained, Google had surveyed customers about their experience after interacting with customer service, but they only got about 15% of people — or one in seven — to complete the survey.

With so few responses, Google was concerned the survey responses weren’t comprehensive or accurate enough to be used as a basis for assessment and improvement.

Zheng’s team built a solution using advanced natural language processing and sentiment analysis to detect how happy, or unhappy, a customer is while on the phone with customer service. That means satisfaction with customer service can be measured live, in real time — no more surveys at the end of the call.

Zheng worked with four Cornell Tech students during a Product Studio last fall.

Beyond enjoying the work with Google, Zheng said she feels the Cornell Tech team respects her role as a designer.

Parsons’ Bakse echoes that sentiment: design is not just a piece of product development, but crucial to the entire experience.

“It is not only important for designers to be part of this process, it is impossible for them not to be,” he said.

The post Parsons, Cornell Tech Students Team Up To Design Real-World Solutions appeared first on Cornell Tech.

One major cause of traffic backups in New York City is double-parked cars, often due to a dearth of legal parking spaces. A study from 2008 found that private vehicles exceeded legal spaces by 30 percent in lower Manhattan — and it stands to reason that the problem has only gotten worse since then.

It’s an issue that Sidewalk Labs, a company dedicated to solving problems in the urban environment, wanted to explore. So the company challenged a team of Cornell Tech students to solve it.

As part of Cornell Tech’s Product Studio course, four students — Greg Pekar, Operations Research and Information Engineering ’17, Diego Wolfsdorf, Computer Science ’17, and Jeff Clement and Gustavo Lozano, both Johnson Cornell Tech MBA ’17 — formed a team to tackle gridlock.

“Our team was tasked with reducing congestion and improving safety by detecting where double parking occurs,” said Clement.

Developing a Prototype

The group’s first idea involved creating a parking reservation system. This solution, however, was ultimately too expensive and complicated to implement.

Next, the group experimented with a pricing system: prime parking spots, at peak times, would be priced accordingly. When this, too, proved larger than the course’s semester-long scope, the team found itself back at the drawing board.

“Going back to square one can be overwhelming,” said Clement. “When we found ourselves stuck, [Cornell Tech Designer-in-Residence] Leland Rechis helped us reframe the question, and just talked things through so that we could keep moving forward.”

The app records a cyclist’s trip and uses the data of the movement and speed to make track traffic congestion.

After thinking about why their previous ideas didn’t pan out, they realized that lack of data around parking was central to the problem of improving congestion.

Eventually, the team decided to aggregate and map various traffic data points, and built a system to process this information. That meant equipping Citi Bikes with smart handlebars — handles with built-in sensors — accelerometers, and GPS to log riders’ movements. That way, if a rider’s trajectory showed them dodging car-sized obstacles where bike lane should’ve been, the team could infer that a car or truck was illegally parked there.

“The future vision was to have a bunch of Citi Bikes running around to collect this data so that you could pinpoint where there was a likelihood of a double-parked car,” said Pekar. “If a bunch of bikes go down a certain road and they make a certain pattern, there’s probably something in the way.”

From Prototype to Product

Once the team began seeing the results of their prototype and charting the results, they started to build a machine learning algorithm to help with the process.

That led Wolfsdorf to contact Cornell computer science professor Serge Belongie. “I made an appointment with him during office hours [to figure out] the best approach to our machine learning problem,” said Wolfsdorf. “He pointed us in the right direction and told us about other projects with similar data-collection problems.” After looking through other sets of data, the team created an app for the sensor data they had collected and created a hypothetical heatmap based on what the city might look like to bikers using it when they ride.

The final step: taking the data they’d collected, along with their unique technology for Citi Bikes, the team presented their findings to Sidewalk Labs. They met with the Sidewalk Labs CTO Craig Nevill-Manning, former director of engineering at Google’s New York offices.

When a bike swerves to avoid a car-sized obstacle, the program infers that a car or truck is likely illegally parked there.

“We received good feedback from Craig and 12 [other] experts about the project,” recalled Clement. “Sidewalk Labs was excited by our results.”

Though the team completed the challenge during the fall semester, they’re now considering how it might be useful to other organizations or other projects in the near future. “We believe that this has potential — bicycle riding is becoming more and more popular and there are more bike-sharing programs in cities,” said Clement. “A lot of big companies, such as Waze or Uber, might want to know more about what’s on the streets.”

The post How to Reduce Urban Congestion by Tracking Cyclists’ Movements appeared first on Cornell Tech.

When frog design submitted a prompt to Cornell Tech’s Product Studio, the global design strategy and research firm was expecting their assigned team of masters students to focus on raw analytics, and other forms of objective data. Instead, the Cornell Tech team and frog design shifted focus of the conversation back to conversation itself, and produced a groundbreaking transcription service.

An Open-Ended Ask

Hoping to unleash them creatively, frog design’s challenge to the team amounted to an open-ended question: how could wearables and sensors enable design researchers to draw more valuable insights while in the field?

“They didn’t give us technology, or any ideas beyond that question. It was our role to dig down deeper, and figure out what we need to do,” said team member Gabe Ruttner, Master of Engineering in Computer Science ‘17. “We had to run with that, figure out what it means, unpack the different terms, and come up with a product that addressed that question.”

Pond’s transcription feature lets you capture and curate conversations in real-time with custom tags.

The Breakthrough Moment

This creative license led the team to think critically about their prompt — and eventually, to reframe the challenge altogether.

“We actually didn’t use wearables, we spun away from that early on,” said Ruttner.

The team realized that a surplus of data, rather than providing clarity, more often has the effect of obfuscating meaning. So the team turned its attention to more accurately capturing human interactions, as opposed to, say, devising new ways of collecting data.

“There was a moment where we said, ‘Humans are the best sensors’ — and it sort of fell in place for us,” recalled Brinna Thomsen, Parsons, BFA Communications Design ’18.

Users organize quotes into relevant categories and elevate the quotes that embody key insights from their research.

Building a Product Solution

The team divvied up responsibilities based on their respective fields of study, with Ruttner and Roy Cohen, Technion-Cornell Dual Master’s Degrees in Connective Media ’18, working as developers, Thomsen heading up design, and Vince Wong, Johnson Cornell Tech MBA ‘17, serving as product manager.

“We all sort of merged together,” said Ruttner.

Working closely over a series of weeks with frog’s design researcher Lola Bates-Campbell, the students developed a transcription app that the group named ‘pond’, a nod to the company that spawned it. ‘pond’ is a real-time transcription program that allows an interviewer to easily flag relevant information with custom tags and then curates that information into insights.

With a print to post-it note feature, pond allows users to move seamlessly between synthesizing in the physical world and the digital world. When they are finished grouping the insights, they can quickly bring those categorized groups back into pond by scanning QR codes located on the post-it notes.

Users can print relevant quotes to post-it notes, synthesize them in the physical world, then scan them back into pond for further analysis or use in presentations.

The app, developed using Django — a free, open-source framework — and Google’s Speech API, is in the public domain, a decision made by the company and backed by its creators.

Reflecting on the process, the students recognized that, in some ways, the opportunity to work on a research tool made their experience especially valuable. “Our project was kind of meta in the sense that we were doing for frog what frog does for their clients,” said Ruttner.

Wong agreed, “I think frog was very excited to mentor us under their own design research methodology as we built pond for them. They were incredibly supportive from end-to-end.”

The post Using ‘Human Sensors’ to Synthesize Qualitative Data appeared first on Cornell Tech.

But last semester, a team of Cornell Tech masters students built a life-saving resource with the help of the NYC Mayor’s Office to Combat Domestic Violence.

The office challenged Anna McGovern, Johnson Cornell Tech MBA ‘17, Jayna Patel, Master of Laws ‘17, Renkai Xiang and Wujing Yao, both Master of Computer Science ‘17, with the following question:

How might we create a mobile application that provides comprehensive and multidisciplinary information, tools and resources for domestic violence victims/survivors while also protecting their safety and privacy?

Their company mentor Hannah Pennington, Director of Policy, Mayor’s Office to Combat Domestic Violence, worked closely with the team over the course of the semester to build a digital resource for victims and survivors of domestic abuse.

“What really strikes me about this team is their willingness to dig in on this issue that actually not all them knew a lot about and their real commitment to becoming more expert in it,” Pennington said.

The resulting product is a safe and easy-to-use web application that provides victims with helpful information and access to Family Justice Centers.

“We learned from our caseworker interviews is that there was kind of a link missing,” McGovern said. “There’s people that have the courage to walk into one of these [Family Justice Centers], but then there are all these other victims out there that don’t understand what the centers can offer them and what resources are available and we needed to find a way to bridge that gap, virtually.”

The post Product Challenge: NYC Mayor’s Office to Combat Domestic Violence appeared first on Cornell Tech.

The exact challenge was:

How might we apply speech, natural language processing or machine learning to create innovative experience to better assist customers who call Google for support?

The team that took on this challenge included: Hong Gan, Masters in Computer Science ‘17, Trishala Neeraj, Technion-Cornell Dual Master’s Degrees in Connective Media ‘18, Elya Pardes Master in Computer Science ‘17, Ruth Sylvia, Johnson Cornell Tech MBA ‘17, and Jia Zheng, Master of Fine Arts, Design and Technology, Parsons School of Design ‘17.

Working with Paul Hahn, Sr. Manager of Customer Support Applications at Google, the team developed a solution using advanced natural language processing and sentiment analysis to detect how happy, or unhappy, a customer is while on the phone with customer service. That means satisfaction with customer service can be measured live, in real time — no more surveys at the end of the call.

“The problem that we posed is a bit ambitious, which is our nature at Google,” Hahn said. “I was curious to see how the students with a fixed amount of time would tackle that and to what extent they might pull back. They didn’t and I was a little surprised…and impressed.”

The post Product Challenge: Google CIO appeared first on Cornell Tech.

Add in the need to balance a team with the right skill sets and interests, and the process gets even trickier.

But one team of students at Cornell Tech actually built a tool to make this matching easier and more efficient.

As part of her Startup Studio project last year, Angel Wong, Master in Computer Science ’16, and her teammates Derek Cutting, MBA ’16, and Yu-chien Chan, Computer Science ’16, built “Dreamteam”—an open source algorithm capable of creating teams of students with balanced skill sets, and pairing them to specific projects that fit their interests.

It quickly became clear that while the product had a lot of applications, it would be particularly useful at Cornell Tech where students work in teams all of the time.

The program went live in August to match Product Studio teams. Since then, students have been clamoring for its deployment in other courses and several companies participating in Product Studio have applauded its results as well.

“One organization said to me, ‘It’s really great how passionate these students are [about their company challenge projects],'” said J McLoughlin, Cornell Tech’s Studio Director who oversees the studio programs at the school. Dreamteam helped match students with the projects they really cared about. “[The students are] not just going through the motion of a class exercise.”

The best match
At its core, Dreamteam is a matching tool. Cornell Tech students are constantly working in teams, and many of these teams rotate throughout the school year, depending on the class. For example, in Startup Ideas, teams change weekly. In Startup Studio, where Wong first developed Dreamteam last year, teams meet for the entire semester.

Building those teams, and ensuring their diversity—that there aren’t too many engineers or MBAs—originally fell to McLoughlin. While the algorithm she used to do so was functional, it was nothing compared to Dreamteam.

How well does Dreamteam work? For the first semester of the 2016–2017 school year, 99 percent of students were placed with one of their top four choices in Product Studio.

Dreamteam’s goal, as the name suggests, is to build a “dream team” of students who are evenly matched, well-suited to each other, and have strengths that dovetail with those of others to produce optimum results. While student satisfaction is key to success, other factors come into play as well, such as whether or not a student has coding ability, or what they are studying.

“Well-balanced teams make students happy to work on projects,” said Wong.

All about the team
The ability to work in a team environment, across multiple disciplines, is today considered a necessary skill in the workplace. No longer do tech advances come from back rooms filled with coders and engineers. Success is an amalgam of inputs: design ideas, communication strategies, business concerns, technological know-how. In this context, the ability to sit across a table and communicate with coworkers from other departments—from marketing to engineering—is paramount.

“[Communication] is a great skill to learn in an educational setting and apply to the work after you graduate,” said Wong. “[Product Studio] is a brief taste of that life skill in play within a school setting.”

Dreamteam helps piece together the foundations of that student experience.

In McLoughlin’s eyes, Wong’s student project was a gem unearthed from their own program’s soil. She was sold not only on Dreamteam’s algorithm, but also its user interface, which presented a clean and simple front-facing tool for students to access over the web.

(From left to right) Cutting, Chan and Wong working on MatchKit, the predecessor of Dreamteam, during a Studio Sprint in spring 2016.

Previously, students had been notified of their team assignments only after these had been generated and stored on Excel spreadsheets. With Dreamteam, results are posted online, and students can check on their teams whenever they choose—they can even look up former team members and contact details.

Given that some teams change weekly, this new approach has been a game changer, McLoughlin said. “Since students are coming from different degree programs, they’re able to meet each other. And if you ever want to email someone from another team, you can go into Dreamteam and look back at that. ”

Happy teams, happy companies
Cornell Tech hired Wong after she graduated to join its in-house development team, The Foundry for the summer. There, working alongside Jai Chaudhary, Master in Computer Science ’15, she fine-tuned the tool so that Dreamteam could launch when classes started this fall. And she will continue to work on the next iteration of the tool, expected fall 2017.

McLoughlin says that companies are already reporting how pleased they are with the level of energy and engagement of student matches facilitated by Dreamteam. She also points out that in a sense Cornell Tech should be seen as the most successful match of all: in the course of teaching students how to collaborate as a team, the institution built a tool — in house and through collaboration — that enhanced its work and strengthened its mission.

“We are practicing what we preach,” said McLoughlin. “Angel did her project, then we hired her, did product development and rebranded Dreamteam for Cornell Tech. So we’re doing the same thing our students are, but our output is to help the Studio curriculum.”

The post Cornell Tech Alum Builds ‘Dreamteam’ to Create All-Star Tech Teams appeared first on Cornell Tech.

Cross-program teams work together with guidance from their company mentor to answer these questions using technology. The fall semester course is designed to give students experience working through real-world problems to develop viable solutions.

“From the company challenge with AppNexus, I learned the importance of holistic thinking in solving a problem,” Claire Opila ‘17, a connective media student, said. “It is critical to understand the entire ecosystem that gives rise to this issue so that it can be properly and entirely addressed.”

Choose Your Challenge
App Nexus: How might we help knowledge-workers develop and maintain a state of “flow”?

Bloomberg: How might we improve and productize sarcasm detection?

Citi: How might we design an authentication experience in which [the attacker] cannot figure out when and where the authentication challenge occurs?

Robin Hood Foundation: How might we create a new online marketplace that harnesses the power of the sharing economy to benefit low-income wage earners?

Weight Watchers: How might we tackle teenage weight loss without teens feeling like they are on a program?

Verizon: How might we play at the intersection of advertising and the internet of things by combining AOL and Verizon technologies?

The App Nexus Challenge: How might we help knowledge-workers develop and maintain a state of “flow”?

In the modern workplace, technology has exponentially increased the number of services competing for our attention. To combat the endless stream of interruptions and notifications distracting workers throughout the day, the 2016 company challenge from AppNexus asked Cornell Tech students to facilitate focus in the workplace.

In response the challenge, Team App Nexus looked outside of technology to approach the problem holistically. After observing and interviewing developers at App Nexus in their natural work setting, the team began by testing a few initial ideas. They soon realized that difficulty maintaining focus was both a real-world and a technological problem. That is, the office layout and culture is as much an issue as all of the emails, texts and ‘slacks’ people receive. This early realization helped them determine that they needed both physical technological components to address real-world and digital distractions. What resulted was an application called “Flow” that enables highly technical workers to maintain focus and increase productivity.

With the iMac and iPhone application “Flow,” users trying to focus on tasks receive notifications (text, email, Slack, etc) in the form of customizable digests. The iPhone application is propped up by a tripod on the user’s desk to show colleagues when they do not want to be disturbed. Users not “in flow,” are able to see statuses of other team members within the app so they know who is currently available or unavailable to chat. The goal of this workflow is to carve out the space and time for people to truly be productive, while still staying engaged in the workplace.

Bhagya Canumalla, Connective Media ‘17; Jeehyun Kim, CS ‘16; Claire Opila, Connective Media ‘17; James Shen, MBA ‘16; Vivek Sudarsan, CS ‘16

Back to the Top

The Bloomberg Challenge: How might we improve and productize sarcasm detection?

If you’ve ever read the Amazon reviews for the Hutzler 571 Banana Slicer, you understand why companies might want to weed out sarcastic comments.

That’s the problem Team Bloomberg sought to solve.

The journey to TrueRatr was quite multi-directional.The team first imagined TrueRatr as a sentiment analysis engine (similar to Crimson Hexagon & Radian 6), then as a potential dating app assistant, then as a cyberbullying/troll detection library, then as a non-profit open source project (the Open Sarcasm Project ala the Human Genome Project).

The twists and turns of Team Bloomberg’s product development roadmap reflect the discovery-oriented approach that that Greg Pass and Leland Rechis advocate in the studio.

It was only after the first Studio Sprint — a designated 24-hour period every month for teams to make rapid progress — that the team decided to target sarcasm detection in online reviews. They were first drawn to the prospect of detecting sarcasm in Amazon product reviews, but it proved to be too broad a space (too many banana slicers), so they refocused to app reviews on iTunes.

At each stage, the team evaluated the feasibility of creating a working prototype within the 3-month semester. Given the fact that data on sarcasm is hard to find, they needed to zoom in on one area to identify patterns of sarcasm, collect sarcastic and non-sarcastic data and then train their model. Using Amazon’s Mechanical Turk marketplace to collect some of this data, their eventual training set had 1,188 reviews.

In a nutshell, their TrueRatr engine does 3 things:

• Broke down product review text into smaller parts or “tokens”.
• Performed sentiment analysis on each of these “tokens” and identified sentiment shifts (e.g. “I love being yelled at! Yay!” would be positive-negative-positive (I love – being yelled at – Yay!)
• Tested these patterns of sentiment shifts against a Machine Learned pattern, that they had trained on the previously-collected data.

If the product finds any reviews to be sarcastic, it throws them out, and recalculates a rating for an app, termed its “True Rating.”

Read more about TrueRatr in ArsTechnica.

Karan Bir, MBA ‘16; Ming Chen, CS ‘16; Hesed Kim, MBA ‘16; Shreyas Kulkarni CM ‘17; Brendan Ritter CS ‘16; Mengjue Wang, Connective Media ‘17

Back to the Top

The Citi Challenge: How might we design an authentication experience in which [the attacker] cannot figure out when and where the authentication challenge occurs?

Passwords. Everybody has them and everybody forgets them.

So when Citi challenged a team of Cornell Tech students to improve this system, it wasn’t an easy task.

In response to this challenge from Citi, students developed CitiMesh, a passwordless authentication system that creates a digital fingerprint for a user based on their Internet of Things network and gathered data points.

Unlike password authentication systems, the Citimesh user doesn’t have to remember anything, as the system makes the whole experience passive and seamless. Because there is no password to guess or steal, CitiMesh is more resilient to system-wide database attacks than a password protected system.

CitiMesh was designed for enterprise and commercial use. The software connects a user’s bluetooth-enabled devices using beacons to gather IP address and geolocation information. Then, a confidence score is calculated to determine likelihood of a user being the correct person accessing the account. If the user’s confidence score is above a safe threshold set by Citi, then the user simply presses the confirm button that appears on their smart device to access their account. This approach provides the user with a seamless and more secure authentication experience, without the anxiety of having to remember complicated passwords.

Murat Akdeniz, MBA ‘16; Chloe Eghtebas CS ‘16;, Carlos Fernandez, MBA ‘16; Jocelyn Kong, CS ‘16; Sasinda Premarathna, Connective Media ‘17

Back to the Top

The Robin Hood Foundation Challenge: How might we create a new online marketplace that harnesses the power of the sharing economy to benefit low-income wage earners?

It seems like every day a new startup pops up to do your laundry or clean your home. Beautifully designed apps and websites make it convenient for users to order their services seamlessly.

But what about low-wage workers who depend on customers to support themselves and their families? Without the technical skills to build an app, they are often left behind and replaced by sleeker, simpler competition.

This was the Robin Hood Foundation’s challenge for one Cornell Tech team.

The team first unpacked this challenge by talking to several Robin Hood grantee organizations to better understand their experiences working with the community of low-income wage earners in NYC.

The team then looked for common themes to build the product concept. Initially, these conversations led them to believe the factors preventing inclusion in the sharing economy were the lack of bank accounts, awareness and access to technology. However, these notions proved false. In fact, the team found that these workers, despite having bank accounts and Android phones, believed that the current online service opportunities could not provide a living wage.

Team Robin Hood Foundation decided to leverage the power of worker-owned cooperatives — a proven mechanism to lift low income workers out of poverty — for the digital sharing economy.

In a co-op, workers join together to create a brand and provide a single service, like house cleaning, for which they can demand a higher price. Additionally, the worker-run and owned co-ops offer workers a community of support, the opportunity for training, autonomy and accountability.

After discovering the empowering world of worker cooperatives, the team decided to build Coopify, a device-agnostic mobile-first platform, which was uniquely targeted towards co-ops. The app gives co-ops the ability to coordinate their services and scale their business. To help the group understand their target user, The Center for Family Life worked with the team to coordinate focus groups with co-op members. They tailored a solution to meet the needs of coop members with features that included support for multiple languages and added functionality to allow for cash payments.

As the fall term came to a close, Robinhood recognized that the Cornell Tech student-developed solution could be viable in the market brought on staff for further development to bring the app into production. With the continued help of Center for Family Life, the Robin Hood Foundation plans to launch this summer.

When it’s released, Coopify will allow co-ops to compete against other service apps and transform this socially-responsible framework into a platform that leverages technology and empowers workers.

Read more about Coopify in Fast Co.Exist.

Melina Diaconis, MBA ‘16; Ron Fisher, MBA ‘16; Harrison Gregg, Connective Media ‘17; Ashwin Ramanathan, CS ‘16; Jared Sharfin, MBA ‘16

Back to the Top

The Weight Watchers Challenge: How might we tackle teenage weight loss without teens feeling like they are on a program?

Ever tried getting a teenager to do something? Now imagine trying to encourage them to eat healthy or exercise regularly. This is the challenge Weight Watchers posed to our students..

The Weight Watchers team realized that to attack teen obesity, they needed to broaden their focus beyond weight loss and approach the question more holistically. How could they inspire teens to make healthy choices? With 44 million teens living in the US today, the team hoped to develop an app that had the potential to have a substantial impact on teens and their families.

They began by focusing on the end-users of this challenge, speaking to 80 teens over the course of the semester. The team then coupled these user studies with external research on teen health, developing an app called Apple-A-Day. Designed as a go-to, no-pressure space for teens to discover new and exciting healthy lifestyle activities, the app also challenges teens to complete one activity per day.

The app was designed to be dynamic and customizable so WeightWatchers could leverage its immense media library of healthy lifestyle content to create new challenges for teens and their families.

Kate Bodden, MBA ’16; Eric Conti, MBA ’16; Meghan Servello, MBA ’16; Yuxi Shen, MEng ’16; Daniel Speiser, MEng ’16

Back to the Top

The Verizon Challenge: How might we play at the intersection of advertising and the internet of things by combining AOL and Verizon technologies?

So you went on a “rad” snowboarding trip and now you want to edit all your GoPro footage together to brag on Facebook? Well, have fun wading through 8 hours of footage looking for that one time you landed that “sick” jump.

Or maybe you don’t have to do that because a team of Cornell Tech students may have saved you the trouble.

In response to the challenge from Verizon, Team Verizon built Velozity, an iOS application that uses the sensors in your mobile device to capture the timestamp bands of stark changes in body movement and snip out the video footage corresponding to those timestamps. By simply pairing the app with a GoPro, Velozity can create a highlight reel that clips the time you got 10 feet of air so you can easily share it with your friends without having to go back and manually edit through an entire day’s worth of footage.

The idea for Velozity came after Team Verizon discovered that last year, wearable sales were up 76 percent in the action sports market, and on the slopes, action camera sales have doubled in the past four seasons. Tons of data and video footage is collected every minute, and while users have the means to share video, most of the data goes unused.

After reporting the project back to Verizon and discussing potential next steps, the team suggested building out the backend using Verizon Digital Media Services to allow users to create profiles and share their adventures. Since then, Verizon has gone on to file a patent application with the idea. Hopefully, in the near future, you’ll be able to use Velozity to easily identify and share your highlight moments with the world.

Julian Ferdman (MBA ’16), Kuo-Wei Tseng (CS ’16), Shawn Bramson (CM ’16), Margaret Barnes (MBA’ 16), Jean-Charles Gasche (CS ’16)

Back to the Top

The post 6 Cool Products Built During Company Challenges appeared first on Cornell Tech.