DADivya Aggarwal

Divya Aggarwal

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Divya Aggarwal has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Text‐Based Investor Sentiment in Asset Pricing: A Survey of Belief Formation Mechanisms

    by Sougata Banerjee, Divya Aggarwal

    Text‐based investor sentiment has become a widely used explanatory variable in asset pricing, yet its economic interpretation remains unsettled. A large empirical literature documents that sentiment measures derived from news, corporate disclosures, and social media predict short‐horizon returns, affect volatility, and explain trading activity. These findings are often interpreted as evidence of sentiment‐driven mispricing, but such conclusions depend on assumptions about how investors form, process, and revise beliefs. This survey re‐evaluates the literature through a mechanism‐based framework that distinguishes between competing channels of belief formation, including non‐fundamental demand, biased beliefs, rational information aggregation, attention and salience, and feedback effects. We show that similar empirical regularities can arise from fundamentally different economic mechanisms and therefore require careful theoretical interpretation. The survey clarifies the role of machine‐learning‐based sentiment measures, highlights the limits of interpreting predictability as market inefficiency, and provides a framework for linking sentiment evidence to coherent asset‐pricing models.

  • Open Access

    Predicting EU Emissions Allowance Prices Using Macroeconomic Indicators and Hybrid AI Models

    by Saptarshi Ganguly, Pooja Sengupta, Divya Aggarwal

    Predicting carbon allowance prices has grown more crucial in relation to carbon market regulation, financial strategy, and environmental policy development. This study examines a hybrid forecasting system that combines deep learning with ensemble machine learning models to forecast the price fluctuations of EU Emissions Allowance (EUAs) within the European Union Emissions Trading System (EU ETS). By leveraging a dataset that includes past EUA prices alongside macroeconomic factors like exchange rates, stock indices, natural gas, and crude oil prices, we evaluate the forecasting capabilities of long short‐term memory (LSTM) neural networks, random forest (RF), and extreme gradient boosting (XGBoost) models. These models are assessed using commonly recognized metrics: root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The findings suggest that LightGBM and XGBoost outshine Random Forest and LSTM in performance, with XGBoost emerging as the best predictor model. XGBoost specializes in capturing complex connections within structured data by managing nonlinear connections and interactions. Considering that carbon markets operate in phases, with each phase bringing its own set of reforms, this study offers novel results. In an integrated market prediction of evolving asset class series, LSTM models that are considered more adept at handling sequential data like time series might not yield superior forecasting performance. Our results emphasize the capability of ensemble learning approach forecasting systems to improve prediction accuracy in emissions trading markets, providing important information for policymakers, financial analysts, and sustainability strategists. The hybrid method discussed here demonstrates how AI‐based analytics can enhance more resilient and data‐informed environmental decision‐making.

  • Forecasting of S&P 500 ESG Index by Using CEEMDAN and LSTM Approach

    by Divya Aggarwal, Sougata Banerjee

    This study aims to forecast the S&P 500 ESG index using the mixture model of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and long short‐term memory (LSTM) prediction models. CEEMDAN enables decomposing the index's original return series into different intrinsic mode functions (IMFs) and a residual series. The decomposed IMFs are then regrouped into aggregate series depicting high frequency and medium frequency, while the residual series represent the trend component. LSTM algorithm is used on the aggregated series to obtain predicted values of the same. The study compares different prediction algorithms to identify their performance and explore the predictive power of the hybrid models.


  • Shrinking the capital costs and beta risk impediments through ESG: study of an emerging market

    by Santushti Gupta, Divya Aggarwal

    Purpose: This study aims to empirically examine environment, social, and governance (ESG) as an effective strategy to reduce major impediments for a corporation in the form of costs of capital (COC) and systematic risk, especially for emerging markets such as India.Design/methodology/approach: A sample of 114 Indian firms from eight prominent industries based on Thomson Reuters classification (TRBC) are used in the study. A panel regression with industry-fixed effects is carried out to account for industry heterogeneity. For robustness, the authors also carry out a matched sample analysis.Findings: The authors observe a negative and significant relationship between ESG performance with COC and systematic risk, respectively. For the pillar-wise analysis, the authors observe that only governance performance is negatively and significantly related to COC whereas the environmental and social performances are negative and insignificant. For ESG pillar level analysis for beta, the authors observe that all pillars are negative and significant, thus making a case for how firms can fine-tune their ESG strategies according to each pillar.Research limitations/implications: As the ESG concept is still in a very nascent stage, data availability is a definite challenge in India.Practical implications: As ESG is increasingly becoming relevant for multiple stakeholders, this study aims to provide evidence that can potentially guide the regulators, practitioners, and academicians to address the contemporary needs of these stakeholders, while also doing good for the firm in the traditional sense.Social implications: The transition to a sustainable economy is a challenge for emerging economies, especially for a country like India where stakeholders are not only varied but also huge in number. With this study's contribution towards an incremental understanding of ESG, Indian regulators and policymakers can bring forward mandates as to ESG compliances that are rewarding for the firms and give them enough impetus towards complying with ESG norms.Originality/value: The extant literature on ESG majorly discusses the relationship between ESG performance and financial performance. This study addresses the lacuna of the relationship of ESG with COC and beta in the Indian context.


  • Examining significance of “downside beta” as a measure of risk – evidence from Indian equity market

    by Sivakumar Menon, Pitabas Mohanty, Uday Damodaran, Divya Aggarwal

    Purpose: Many studies have shown that from a theoretical and empirical point of view, downside risk-based measures of risk are better than the traditional ones. Despite academic appeal and practical implications, downside risk has not been thoroughly examined in markets outside developed country markets. Using downside beta as a measure of downside risk, this study examines the relationship between downside beta and stock returns in Indian equity market, an emerging market with unique investor, asset and market characteristics.Design/methodology/approach: This is an empirical study done by using ranked portfolio return analysis and regression analysis methodologies.Findings: The study results show that downside risk, as measured by downside beta, is distinctly priced in the Indian equity market. There is a direct positive relationship between downside beta and contemporaneous realized returns, indicating a premium for downside risk. Downside risk carries a higher weightage than upside potential in the aggregate return of the stock portfolios. Downside beta is a better measure of systematic risk than conventional market beta and downside coskewness.Practical implications: The empirical results support the adoption of downside beta in practice and provide a case for replacing traditional beta with downside beta in asset pricing applications, trading and investment strategies, and capital allocation decision-making.Originality/value: This is one of the first in-depth studies examining downside beta in Indian equity markets using a broad sample of individual stock returns covering a wide time range of 22 years. To the best of our knowledge, this study is the first one to compare downside beta and downside coskewness using individual stock data from the Indian equity market.


  • YES Bank Fraud: Examining the Softer Underbelly of the Fraud from a Behavioral Model

    by Nistala Jagannath Sharma, Divya Aggarwal

    Poor corporate governance, insufficient regulatory supervision, and lack of compliance are susceptible factors for fraudulent activities in the Indian banking sector. This study examines the role of softer aspects like the CEO's personality traits that instigate an organization's involvement in fraudulent activities. Our study proposes a conceptual model to examine the behavioral fabric of fraud by widening the scope of the existing corporate fraud models. The conceptual model is built upon three primary components: dark personality traits of the CEO leading to CEO hubris, internal firm factors, and external firm factors. The proposed model aims to analyze the massive fraud done at YES Bank, considered a pioneer for the Indian private banking sector. The study aims to contribute toward existing fraud theory literature by proposing a new model. It aims to contribute to the increasing sensitivity of forensic accountants toward examining the psychological and behavioral traits of a fraudster.


  • Compliance Behaviour Amidst Ambiguous Information: An Exploratory Study in the Context of COVID-19

    by Divya Aggarwal, Subramania Raju Rajasulochana, Varun Elembilassery

    COVID-19 pandemic is an ambiguous situation due to the uncertainty associated with the outcome of the situation. This article aims at exploring the knowledge behaviour gap during a pandemic like COVID-19. The findings of this study indicate that individuals perceive different forms of ambiguity in different ways. Findings also suggest that, during a pandemic, attitude towards ambiguity and confidence in self-health significantly impact compliance behaviour. Interestingly, the findings also indicate that knowledge and perception about the context are not significantly associated with compliance behaviour. This study is one of the earliest attempts to understand the knowledge behaviour gap during a pandemic and contributes to the research literature by attempting a cross-fertilization of concepts from different streams of literature. This study also discusses the practical implications for the health sector, in particular health communication. JEL Codes: C9, D10, D81, D90