Faculty & Research

Research Productive

Show result

Search Query :
Area :
Search Query :
887 items in total found

Journal Articles | 2026

Predictive Hotspot Mapping for Data-Driven Crime Prediction

Karthik Sriram, Ankur Sinha, Suvashis Choudhary

Predictive hotspot mapping is an important problem in crime prediction and control. An accurate hotspot mapping helps in appropriately targeting the available resources to manage crime in cities. With an aim to make data-driven decisions and automate policing and patrolling operations, police departments across the world are moving toward predictive approaches relying on historical data. In this paper, we create a nonparametric model using a spatiotemporal kernel density formulation for the purpose of crime prediction based on historical data. The proposed approach is also able to incorporate expert inputs coming from humans through alternate sources. The approach has been extensively evaluated in a real-world setting by collaborating with the Delhi police department to make crime predictions that would help in effective assignment of patrol vehicles to control street crime. The results obtained in the paper are promising and can be easily applied in other settings. We release the algorithm and the dataset (masked) used in our study to support future research that will be useful in achieving further improvements.

Read More

Journal Articles | 2026

FinBloom: Knowledge-Grounding Large Language Model with Real-Time Financial Data

Ankur Sinha, Chaitanya Agarwal, Pekka Malo

Large language models (LLMs) excel at generating human-like responses but often struggle with interactive tasks that require access to real-time information. This limitation poses challenges in finance, where models must access up-to-date information, such as recent news or price movements, to support decision-making. To address this, we introduce Financial Agent, a knowledge-grounding approach for LLMs to handle financial queries using real-time text and tabular data. Our contributions are threefold: First, we develop a Financial Context Dataset of over 50,000 financial queries paired with the required context. Second, we develop FinBloom 7B, a custom 7 billion parameter LLM, by fine-tuning Bloom 7B on 14 million financial news articles from Reuters and Deutsche Presse-Agentur (DPA), alongside a random sample of 25% from 12 million Securities and Exchange Commission (SEC) filings. Third, we fine-tune FinBloom 7B using the Financial Context Dataset to serve as a Financial Agent. This agent generates relevant financial context, enabling efficient real-time data retrieval to answer user queries. By reducing latency and eliminating the need for users to manually provide accurate data, our approach significantly enhances the capability of LLMs to handle dynamic financial tasks. Our proposed approach makes real-time financial decisions, algorithmic trading and other related tasks streamlined, and is valuable in contexts with high-velocity data flows.

Read More

Journal Articles | 2026

Policy Evaluation in the Absence of Survey Data: Customised Border Designs With Satellite Data

Muddasir Ahmad Akhoon, Abhishek Shaw, Vidya Vemireddy

Developing country governments often launch new agricultural programmes without collecting pre-implementation survey data, making it difficult to evaluate the effects of such programmes. Leveraging the flexibility of granular pixel-level satellite panel data and a well-developed quasi-experimental policy evaluation design, we study a programme where pre-implementation data is unavailable. We estimate the effect of cash transfers on agricultural productivity in Telangana, India. Treatment and control regions are within 10 km on either side of the state border. They are identical in all respects except for the difference in exposure to policy treatment. Agricultural productivity increased in the major monsoon cropping season due to the cash transfer programme. The findings also reveal that cash transfers helped reduce productivity gaps between irrigated and rainfed agricultural areas. Our results are robust to two different sources of satellite data, three alternative indicators of productivity, two rounds of full-scale resampling, 100 rounds of small-scale resampling and three alternative border designs. Placebo regressions of two previous years also confirm our results. This approach to policy evaluation is applicable anywhere satellite data are available in the world.

Read More

Journal Articles | 2026

Preventing Defaults in Response to Deteriorating Bank Health: The Prompt Corrective Action Approach

Nishant Kashyap, Sriniwas Mahapatro, Prasanna Tantri

Prior research shows that borrowers are more likely to default when their banks are financially distressed, particularly where contract enforcement is weak. We examine whether regulatory intervention in the form of Prompt Corrective Action (PCA), which seeks to improve bank health through enhanced monitoring, reverses such defaults. To address this question, we exploit the bright-line entry thresholds in India's PCA regime using a regression discontinuity framework. We first show that such defaults exist in India. Our main result is that PCA intervention significantly reduces such defaults. The result is robust to variation in methodology and alternative definitions of bank health. Our evidence suggests that PCA reduces such defaults by credibly signaling to borrowers the likely restoration of bank health and continuity of lending relationships. Its effectiveness was reinforced by an earlier regulatory reform that improved the timeliness of loan-loss provisioning, enhancing the credibility of enforcement. Overall, our findings suggest that PCA, when underpinned by credible financial reporting, can serve as an effective policy tool to curb strategic defaults.

Read More

Journal Articles | 2026

Supplier concentration and firm performance: the role of relative size, relative reputation, and network position

Amalesh Sharma Alok R. Saboo Sourav Bikash Borah Anirban Adhikary

Firms face a fundamental trade-off in managing their supplier base: consolidating suppliers can streamline operations and reduce coordination costs, yet it may also heighten dependency on a few key suppliers, diminishing bargaining power and value capture. This study measures supplier concentration using an extended HHI index built from Bloomberg SPLC buyer-side cost shares for each Tier 1 supplier. Using this extended HHI framework, we empirically examine how supplier concentration shapes firm performance, drawing on a unique dataset of 216 firms spanning 5 years and 10 industry sectors. Results show that higher supplier concentration significantly undermines firm performance through intensified power asymmetries. However, firms can offset these adverse effects by leveraging three forms of inter-organizational power: relative size (resourcefulness and bargaining power), relative reputation (attractiveness power), and network position (positional power captured by betweenness centrality and clustering). Additionally, preferred supplier programs and multisourcing can further buffer these negative consequences. By applying an HHI-based concentration measure within a power-dependence framework, the study advances research on buyer–supplier dynamics and offers managers and regulators guidance on assessing and optimizing supply chain value creation, and on how supply-base structure and power imbalances shape performance, providing a baseline for understanding vulnerabilities revealed in subsequent disruptions

Read More

Journal Articles | 2026

Stochastic modeling and design of truck platooning strategies considering platoon dynamics

Rashika Gupta, Devika Koonthalakadu Baby , Debjit Roy , Shankar C. Subramanian, Sandip Chakrabarti

Road transportation via trucks is a dominant mode for long-haul freight transport across countries. However, due to their significant dependence on fossil fuels, trucks are a large contributor to carbon emissions. Hence, new technology-driven solutions such as truck platoons are gaining momentum. While platoons promise to reduce fuel costs and emissions, they may increase transportation time due to additional coordination delays, such as the time required for platoon formation. In this research, we examine the performance trade-offs between platoon fuel savings and excess delay costs resulting from waiting for platoon formation among three platoon formation strategies: intermittent, continuous, and opportunistic. We develop a novel Closed Queuing Network model that captures the dynamics of platoons, as well as the stochasticity in truck travel times, and provides realistic estimates of platoon wait times and vehicle throughput. The platoon formation delays and size-dependent travel times are modeled using merging and load-dependent nodes, respectively, and analyzed through a continuous-time Markov chain. Our study provides key insights into the impact of increasing platoon size on performance measures, including system throughput and mean waiting time. With platooning, the network throughput capacity is reduced; however, fuel savings are realized. For a given network topology, we can identify an optimal platoon formation strategy that maximizes the throughput and fuel efficiency, while simultaneously minimizing vehicle waiting costs.

Read More

Journal Articles | 2026

Revisiting technology races: Evidence from Indian healthcare EMR data

Sawan Rathi, Anindya S. Chakrabarti, Chirantan Chatterjee, Anthony Vipin Das, Raja Narayanan

Technology replacement is a frequent feature of firms’ innovation journey. However, the internal working of replacement of an old technology by a new one is typically blurred – with three simultaneously interacting mechanisms – demand-pull, technology-push, and a combination of market and non-market institutions. In this paper, we disentangle them using novel electronic medical records (EMR) data from one of the largest eye-care hospital chains in Asia. Specifically, we study a race between a newer high-end medical scanning technology replacing an older and less costly technology. We exploit the COVID-19 lockdown shock in a natural experiment setup, which led to concurrent shifts in the demand and supply of a medical scanning technology. Demand-pull generated via patients propelled new technology adoption as the supply of new technology increased in tandem. This was a cohort-specific phenomenon on the supply side, with an age-identified cohort of physicians driving the adoption, and the replacement was measurably welfare-enhancing. Fixed price for treatment ensures that the replacement was not driven by market-led incentives. We conclude by discussing management of innovation through demand- and supply-side as a strategy for the firms.

Read More

Journal Articles | 2026

The quality of state governance as a source of international differences in total factor productivity

Akash Issar, Jamus Jerome Lim, Sanket Mohapatra

This paper examines how changes in firm-level total factor productivity (TFP) depend on the quality of state governance. We find robust evidence that an improvement in the quality of state governance by one standard deviation raises the average firm’s TFP by between 9 and 19 percent. We also show that this effect works through improved productive efficiency rather than technological progress. Further decompositions reveal that the key relevant institutions are government effectiveness, rule of law, and democratic accountability. Moreover, the contribution of state governance to TFP dominates that of corporate governance.

Read More

Journal Articles | 2026

A minimum buyback requirement in open market repurchases: Impact on the signaling role

Pranjal Srivastava, Joshy Jacob, Ajay Pandey

The paper investigates the impact of the imposition of a minimum buyback requirement on open market repurchases (OMRs) in India. We extend the signaling model of Oded (2005) by including a minimum buyback requirement and show that it increases the stock price during the repurchase period, relative to a no minimum buyback regime. Accordingly, we find that the regulatory change has led to a significant increase in the abnormal stock returns earned around buyback announcements. Also, insiders increase their purchase of firms’ stock during the buyback execution period relative to the pre-reform period. These findings are consistent with a higher information value of OMR announcements in the minimum buyback regime. We further observe lower market timing through buyback execution, accompanied by a change in the execution-style, implying a weaker instinct for opportunistic buybacks. Our findings suggest that the regulatory change has lowered the “cheap-talk” motives associated with the announcement of open market buybacks.

Read More

Journal Articles | 2026

All That Glitters Is Not Code? Understanding the Predictors of Developer Popularity and Sponsorship on a Social Coding Platform

Praharshita Krishna, Adrija Majumdar, and Indranil Bose

A developer's popularity plays a crucial role in their success within open source software (OSS) communities and their access to sponsorship opportunities. This study seeks to answer the question: which signals have the most predictive power for popularity and sponsorship volume on social coding platforms? Using algorithm-supported abductive theory generation supplemented by qualitative insights from observations and interviews, we arrive at a theory of peer evaluation in OSS communities. We examine a large number of signals and categorize them. The two categories are signaling via self-disclosure through profile signals and signaling via contribution quantity and quality through behavioral signals. The large amount of data available to us allows us to use machine learning techniques to arrive at top-ranking predictors within each category. We generate our theory by finding robust patterns and test our theory using a hold-out sample. Our findings indicate that easily observable credibility-enhancing and approachability-related developer profile signals hold greater predictive importance in shaping popularity. However, harder to observe and more complex behavioral signals show greater predictive importance for sponsorship volume. These results signify that OSS social coding platforms are not meritocratic, as developer self-disclosure significantly influences popularity. In contrast, sponsorship decisions, due to their high cost and irreversibility, depend on within-platform contribution-related signals. This research contributes to a deeper understanding of popularity and sponsorship within peer-to-peer followership networks in OSS communities. Through our research, platforms are better informed about the predictors of popularity and sponsorship and can introduce measures to enhance the meritocratic nature of these communities. Developers who seek influence and sponsorship on the platform can be more strategic about information disclosure and their contributions.

Read More
IIMA