Fraudulent Transaction Detection in Reverse Auction Systems Using Machine Learning and Blockchain-Assisted Anomaly Analysis

View at publisher Summarise with VIRAT
Authors: Prachi Verma, Jeremy Jacob Mathew, Joshua Vinu Koshy, Ann Rachel Koshy, Arrpita Merlin Abbey
Cited by: 0
References: 3

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The advent of widespread electronic procurements and electronic commerce has rendered reverse auction systems imperative in competitive online procurements. Reverse auction requires multiple sellers to continuously lower their bids to secure contracts, a process that drives market efficiency and optimal pricing for purchasers. Nevertheless, the systems are growing more vulnerable to fraudulent behaviors such as collusive bids, identity spoofing, phantom bids, and price manipulation, which compromise fairness, result in monetary losses, and diminish the confidence of stakeholders. In this paper, we propose a hybrid detection framework for fraudulent activities in reverse auction systems consisting of machine learning-based anomaly detection and blockchain-enabled transparency. To identify anomalous bids, we use the unsupervised algorithms such as the Isolation Forest and the Autoencoder, while the blockchain provides immutability and auditability for all the transactions. We evaluate the proposed system experimentally using simulated auction datasets and demonstrate the detection accuracy of the system to be 95.6%, which far surpasses the current state-of-the-art rulebased detection methodology. We show the efficacy of the system in improving the level of transparency, ensuring accountability, and enhancing security and thus building confidence in the electronic auction domains.

Fields of Study & Subjects

Auction Theory and Applications Blockchain Technology Applications and Security Public Procurement and Policy

Publication details

Journal / source
Biennial International Conference on Nascent Technologies in Engineering (ICNTE)
Pages
1–6
Publication date
16 January 2026
Language
EN