Brij Disa Centre for Data Science and Artificial Intelligence


Can an AI Coach Help You Lose More Weight Than a Human Coach: Empirical Evidence From a Mobile Fitness Tracking App

Prof. Anuj Kapoor
Artificial intelligence(AI) assisted tools are increasingly being used in health care contexts to provide advice and motivation. But whether AI can be a good or even better substitute for human involvement in these contexts is an open question. We provide empirical evidence to answer this question specifically in the context of fitness tracking mobile applications (apps). In addition to facilitating the tracking of activity and food intake, such apps provide advice and motivation in the form of targeted messages to their consumers, and this can be done through human coaches or an AI coach. An AI coach allows these apps to scale their offerings to a larger number of consumers, available on demand to consumers, and potentially more finely targeted by leveraging vast amounts of data. On the other hand, human coaches might be better placed to show empathy, and consumers might also feel more accountable to humans. We compare human and AI coaches on their effectiveness in helping consumers achieve their weight-loss goals. Our empirical analysis is in the context of a large-scale mobile app that offers consumers different levels of subscription plans with human and AI coaches respectively, and specifically compares adopters of the two kinds of plans on their weight loss and goal achievement. We address the potential self-selection in plans by employing a matching-based approach. We find, for our sample of almost 65000 consumers that human-based plans do better than those in AI-based plans in helping them achieve their goals, but that this differs by consumer characteristics including age, gender and body mass index (BMI).

High-frequency trading: Measuring latency from big data

Prof. Anirban Banerjee
Over the last decade, the Indian market has seen significant growth in algorithmic trading and more specifically, high-frequency trading (HFT) activity. During this period, we have witnessed a significant change in the trading landscape as presently close to half of the trading volume in the stock exchanges is contributed by algorithms. This rise has not always been smooth as there have been calls for regulations to restrict algorithmic trading activity due to the fear of probable market manipulation.
Latency is considered one of the most important market parameters for HFTs. Using a large novel dataset of order and trade level data from the NSE, we would like to inspect how the latency in the Indian market has changed and if that has caused any shift in the way HFTs operate. We would also like to observe how the different market quality parameters have evolved over this time.

Causes, Symptoms and Consequences of Sociocultural polarization

Prof. Samrat Gupta
The Information and Communication Technology (ICT) provides users unparalleled access to information from around the globe. In spite of demographic differences, people can communicate, express and evolve their opinions on topics ranging from politics to culture. The wide-ranging information exchange on digital media can lead to two scenarios viz. formation of public sphere or formation of echo chambers. While the public sphere, which promotes greater diversity, is a well-researched domain, substantially less research has been conducted on echo chambers in relation to socio-cultural events. Despite the huge affirmative impact of socio-cultural events on society, the proliferation of controversies around them and reinforcement through echo chambers is collectively having malefic effects on societies. Recent controversies around socio-cultural products such as movies, painting, books, cartoons, etc. resulted in serious outcomes. For example, Indian movie Padmavat brought polarization of public perception which further reinforced through echo chambers and escalated into widespread agitations. It led to mass destruction of property and human suffering during agitation. We believe this represents a mounting problem for society, one that is likely to intensify in the era of social media. Thus, understanding the causes, symptoms and consequences of socio-cultural polarization is critical and would be valuable for developing interventions to reduce unhealthy societal and organizational polarisations.

Employee Reviews - A Text Mining Perspective

Prof. Adrija Majumdar
With the emergence of web 2.0, there is a deluge of online text. Technologies like online communities, social media, crowd funding platforms have further contributed to the volume of content. From the firm’s perspective, understanding consumers’ sentiment from the text is of supreme importance. The literature on online reviews has predominantly focused on ascertaining consumer sentiment of a firm’s products and services. We extend this stream of research and focus on analyzing reviews that employees post regarding their organizations. The study will seek to identify different dimensions that employees highlight in their reviews and their association with overall job satisfaction. We further wish to understand if employees’ perception of the firms also impacts the firm’s performance. The unstructured and noisy nature of the text data often poses significant challenges for organizations in leveraging them for decision making. We will employ text mining methods and techniques to quantitatively analyse the large dataset of employee reviews. The research will have implications for both theory and practice.

When A Machine Knows When You Are Happy (vs. Upset)

Prof. Hyokjin Kwak
Artificial intelligence - the creation of human intelligence and beyond - has significantly altered the very nature of our modern business practice. The fascination towards non-living entities ‘thinking and acting’ with human intelligence is still as fresh and exciting as it was in 1956 - the year AI was coined. However, the latest trend on the role of AI has been gradually shifted from analytical brains (intelligence) to social brains (emotion). That is, this trend puts more emphasis on anthropomorphic AI (e.g., humanoid AI robots). In fact, this aspect of ‘humanization (anthropomorphization)' is not new to the field of branding in the marketplace. Marketers strategically imbues nonhuman entities with humanlike emotions, intentions, motivations, and characteristics. In general, prior research on anthropomorphism shows a positive effect of downstream consequences on consumer evaluations when the brand “interacts” with consumers. Hence, this research project attempts to further investigate how “emotion (or affective)” AI can help brand practitioners engage their customers more with their anthropomorphic brands. A machine should be more effective in communicating brand information with consumers when the machine knows how to interact with consumers’ emotional state (e.g., through their face and body).

Models of implied volatility and information content of option prices

Prof. Sobhesh Kumar Agarwalla and Prof. Vineet Virmani
The proposed research project on modeling implied volatility (IV) and understanding the information content of option prices is part of our larger research agenda on studying ways to quantify uncertainty in financial markets, focusing on India. Traders in options markets do not usually quote option prices, but the volatility implied by them. IV is that volatility input to the famous Black-Scholes option pricing formula such that the Black-Scholes prices match the market price of the options. It has been observed that IV is not a constant but varies systematically with strike/delta and expiration date. The shape of the observed relationship between implied volatility and strike is called volatility smile or skew. In this project, we plan to explore various ways of modeling the dynamics of volatility smile using variants of state-space models and the Kalman Filter.

Hiring for the Future – A People Analytics Approach

Prof. Aditya Christopher Moses
The future of work is a critical aspect for many organizations. A 2020 report by the World Economic Forum suggests that among the various challenges faced by organization one of the most critical areas is skill gaps. They argue that skill gaps continue to remain high as in-demand skills across jobs change in the short term. The top skills and skill groups which employers see as rising in prominence in the lead up to 2025 include groups such as critical thinking and analysis as well as problem-solving, and skills in self-management such as active learning, resilience, stress tolerance and flexibility. On average, companies estimate that around 40% of workers will require reskilling of six months or less and 94% of business leaders report that they expect employees to pick up new skills on the job, a sharp uptake from 65% in 2018.

The changing nature of work and the exponential technology development imply that employees need to constantly re-skill and up-skill. In the current environment, while knowledge can be accessed via multiple sources the behaviours to develop oneself become more important. What behaviours will organizations require for ensuring they have a workforce that can reskill and upskill exponentially? This will be the primary area of research for this study.

Using a data-driven approach, this study uses surveys and NLP to understand which behavioural traits enable re-skilling at pace. We will employ text-mining methods and techniques to identify behavioural traits that help in re-skilling. The insights from this will be further validated and tested using a survey instrument administered to a large sample of individuals.

An iterative gradient-based bilevel approach for hyperparameter tuning in machine learning

Prof Ankur SInha
Hyperparameter tuning in the area of machine learning is often achieved using naive techniques, such as random search and grid search that only lead to an approximate set of hyperparameters. Although techniques such as Bayesian optimization perform an intelligent search on the domain of hyperparameters, it does not guarantee an optimal solution. A major drawback of most of these approaches is that as the number of hyperparameters increases, the search domain increases exponentially, thereby increasing the computational cost and making the approaches slow. The hyperparameter optimization problem is inherently a bilevel optimization task, and there exist studies that have attempted bilevel solution methodologies for solving this problem. These techniques often assume a unique set of weights that minimizes the loss on the training set. Such an assumption is violated by deep learning architectures. Our study is on gradient-based bilevel optimization method for solving the hyperparameter optimization problem. The method is general and can be easily applied to any class of machine learning algorithms that involve continuous hyperparameters.

Multi-period Facility Interdiction Problem

Prof Sachin Jayaswal
We propose to study a multiperiod interdiction problem, in which the leader (attacker) with a limited interdiction budget decides the sequence of facilities to interdict (destroy) over time so as to inflict the maximum cumulative damage to the follower. The follower's objective is to serve a given set of demand points from the surviving subset of facilities the minimum cumulative cost across all periods. for this, his decisions include the assignments of demand nodes to the surviving facilities and the allocation of his limited budget to the revival of interdicted facilities and the protection of the surviving facilities against their interdiction in the future periods. The multi-period version of the problem, which is the focus of the proposed study, presents additional complexity due to the leader's interdiction decisions constrained by the follower's protection decisions. The objective of the proposed study is to design efficient exact solution methods for this challenging bilevel integer program.