Better Data Means Better Food
Turning data into predictive models is not a simple task.
Published April 14, 2020
By Roger Torda
Shelf life is an important variable when it comes to snack foods. But how can shelf life be predicted when new products are being developed?
The starting point is often data from taste tests. Turning that data into a predictive model is not a simple task. And that is why PepsiCo, teaming with The New York Academy of Sciences, posed the problem as a challenge to young scientists.
Pallavi Gupta, who is pursuing her PhD in Informatics at the University of Missouri, Columbia, was the Grand Prize winner in the Data Science in Research & Development Challenge. And as a result she will head to Valhalla, New York in the Summer of 2020, for an internship with PepsiCo’s R&D Data Analytics team.
“I love to analyze data,” Pallavi said, quickly breaking into laughter. “I am looking forward to the internship with PepsiCo, to test my skills and to gain additional experience with data analytics using machine learning techniques.”
Competing Against Hundreds of Innovators
Pallavi was among 1,235 registrants in the Challenge. Jhansi Kurma, who recently earned a master’s degree in Business Information Systems from the New Jersey Institute of Technology, came in second.
PepsiCo turned to the Academy to host the competition because of its experience running innovation challenges in science and technology, dating back to 2010. Many of the Academy’s challenges target early career scientists. Other Academy challenges are for high school students.
“The New York Academy of Science-led data challenge has proven to be an excellent way to reach talented data scientists from around the world and have them work on real life challenges together with PepsiCo’s experts. We are looking forward to the 2020 edition and are committed to make this an annual tradition,” says Ellen de Brabander, PepsiCo’s Senior Vice President for Research and Development, said the Data Science Challenge.
The Value of STEM Skills
Large, diverse companies like PepsiCo, value STEM skills across a wide range of job functions.
“In global research and development, our number one output is innovation, and STEM [skills] are critically important competencies to drive innovation,” the company’s James Yuan said in a NYAS webinar titled “Why STEM Professionals are Valuable Across Industries.”
Yuan, Pepsico’s Senior Director, Data Science & Analytics, went on to explain that students joining R&D at the company can pursue work in a wide variety of areas, including product formulation, packaging, process engineering, food safety, quality control, and regulatory affairs.
“In e-commerce and in global business, there are also a lot of opportunities to leverage STEM capabilities for business optimization,” said Eric Higgins, PepsiCo VP, Data Science and Analytics. “We’re talking about media buys, we’re talking about identifying how to best place our products, product assortment, and supply chain optimization.”
A lot of product innovation within this company comes through simply hypothesis testing,” Higgins continued. “Using data science and STEM disciplines, we’re able to automate that process and expand capability, so we can find new ways of innovating. So, in both R&D and on the business side, there are opportunities across the board for people using new methodologies in mathematics, statistics, and computer science.”
Developing a Useful Shelf-Life Model
Competitors in the Challenge were each given a data set from 81 individual shelf-life studies. The data came from evaluations of changes in the taste of snack products as they aged. The goal was to develop a useful shelf-life model that would allow a product developer to predict shelf life based on the product, process, packaging information, and storage conditions related to where the product would be sold.
The competitors had 14 days to complete the challenge. Ten finalists then presented their solutions virtually to a panel of judges, made up of PepsiCo employees from Data Science, R&D, and Human Resources departments.
Pallavi is working toward her PhD, and is using computational and machine learning approaches to study how small non-coding RNA (also known as “small RNAs) – are involved in gene expression regulation. Pallavi said she would take skills from her upcoming internship and apply them to her own research in genomics.
The Data Science in Research and Development Challenge drew entries from 42 countries, especially from the US, Ireland, the UK, Canada and India.
Learn more about The New York Academy of Sciences’ Innovation Challenges.