A new study co-authored by an Illinois Institute of Technology (Illinois Tech) researcher explores the decision-making strategies behind when people choose to stay with what they know and when they decide to try something new. The research sheds light on how individuals balance short-term rewards with the potential benefits of exploring unfamiliar options, with implications for understanding consumer behavior, technology adoption, and innovation more broadly.

A recent study shows that human employees can believe their jobs are at risk and their morale can sink when working with robots, specifically where performance comparisons are involved. Just as employees can divide into cliques -- psychologically identifying themselves with an "in" group they belong to and "out" groups they don't -- humans can feel in competition with robot counterparts and outclassed by them. recent study shows that human employees can believe their jobs are at risk and their morale can sink when working with robots, specifically where performance comparisons are involved. Just as employees can divide into cliques -- psychologically identifying themselves with an "in" group they belong to and "out" groups they don't -- humans can feel in competition with robot counterparts and outclassed by them. Fortunately, companies may be able to ease the discord. One possibility the researchers found, was to assess employee performance against a benchmark. Even more promising though were team-based incentive policies. When study participants were told they were being evaluated and rewarded in a human-robot team instead of individually, their workplace attitudes were not negatively impacted.

Abstract

Purpose – Stock markets are essential for households for wealth creation and for firms for raising financial resources for capacity expansion and growth. Market participants, therefore, need an understanding of stock price movements. Stock market indices and individual stock prices reflect the macroeconomic environment and are subject to external and internal shocks. It is important to disentangle the impact of macroeconomic shocks, market uncertainty and speculative elements and examine them separately for prediction. To aid households, firms and policymakers, the paper proposes a granular decomposition-based prediction framework for different time periods in India, characterized by different market states with varying degrees of uncertainty.

Design/methodology/approach – Ensemble empirical mode decomposition (EEMD) and fuzzy-C-means (FCM) clustering algorithms are used to decompose stock prices into short, medium and long-run components. Multiverse optimization (MVO) is used to combine extreme gradient boosting regression (XGBR), Facebook Prophet and support vector regression (SVR) for forecasting. Application of explainable artificial intelligence (XAI) helps identify feature contributions.

Findings – We find that historic volatility, expected market uncertainty, oscillators and macroeconomic variables explain different components of stock prices and their impact varies with the industry and the market state. The proposed framework yields efficient predictions even during the COVID-19 pandemic and the Russia–Ukraine war period. Efficiency measures indicate the robustness of the approach. Findings suggest that large-cap stocks are relatively more predictable.

Research limitations/implications – The paper is on Indian stock markets. Future work will extend it to other stock markets and other financial products.

Practical implications– The proposed methodology will be of practical use for traders, fund managers and financial advisors. Policymakers may find it useful for assessing the impact of macroeconomic shocks and reducing market volatility.

Originality/value – Development of a granular decomposition-based forecasting framework and separating the effects of explanatory variables in different time scales and macroeconomic periods.