Detecting Insider Trading in the Indian Stock Market: An Optimized Deep Learning Approach

Prashant Priyadarshi () and Prabhat Kumar ()
Additional contact information
Prashant Priyadarshi: National Institute of Technology
Prabhat Kumar: National Institute of Technology

Computational Economics, 2025, vol. 65, issue 6, No 28, 3923-3943

Abstract: Abstract A novel approach is proposed in this study for identifying insider trading in the Indian stock market by classifying multiple multivariate time series financial data using deep learning. The model utilizes multi-channel convolutional neural network (MTC-CNN) and MTC-CNN with Optuna hyperparameter optimization. In order to test the method, insider trading samples from 2001 to 2020 are used, along with corresponding non-insider trading samples from the same period. As a result of our experiments, we found that under the following conditions of 30-, 60-, and 90-day time window lengths, the accuracy of the proposed method are 87.50%, 75.00%, and 62.50%, respectively. It has also been found that using OPTUNA hyperparameter optimization, the false positive rate was reduced by 20% for all the time windows. These accuracy rates surpass those of the benchmark models like logistic regression, random forest, and convolutional neural network, providing evidence that the proposed system is effective in identifying the activities of insider traders. The proposed deep learning model serves as a valuable tool for market regulators and investors in detecting and preventing illicit trading practices, ultimately fostering integrity and fairness in the Indian securities market.

Keywords: Indian stock market; Insider trading identification; Multi-channel CNN; OPTUNA (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10614-024-10697-z Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:compec:v:65:y:2025:i:6:d:10.1007_s10614-024-10697-z

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-024-10697-z

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().