Home   >   CSC-OpenAccess Library   >    Manuscript Information
Retail Sales Anomaly Detection: A Machine Learning Approach
Kailash Thiyagarajan, Sivasai Nadella
Pages - 84 - 95     |    Revised - 30-04-2025     |    Published - 01-06-2025
Volume - 19   Issue - 3    |    Publication Date - June 2025  Table of Contents
MORE INFORMATION
KEYWORDS
Anomaly detection, Machine learning, Retail domain, Sales analysis, Outliers.
ABSTRACT
This study analyzes three years of daily transactional retail sales data from stores across various U.S. cities and states. Key variables include transaction amounts, product types, store locations, promotional offers, and holiday-based sales patterns. These factors contribute to detecting anomalies that could indicate fraudulent transactions, accounting errors, or shifts in consumer behavior.

A combination of supervised and unsupervised machine learning models was employed to identify anomalies. Decision trees and random forests classified sales transactions based on labeled historical data, while unsupervised methods like k-means clustering and DBSCAN were applied where labels were unavailable. A hybrid approach combining both methodologies was implemented to improve detection accuracy. This hybrid framework uniquely integrates clustering and classification mechanisms with a real-time notification system, addressing both known and unknown anomaly patterns in retail sales data.

The primary research question this study addresses is: 'Can a hybrid machine learning framework significantly improve the detection of sales anomalies in dynamic retail environments?'

The analytical process leveraged Python libraries such as scikit-learn, TensorFlow, and Keras. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics.

The proposed approach offers practical benefits, including enhanced fraud detection, better inventory optimization, and real-time alerting, thus aiding operational efficiency for retail businesses.

This study underscores the effectiveness of machine learning in detecting sales anomalies, enabling businesses to uncover fraudulent activities and operational inefficiencies.
Ahmed, M., Mahmood, A. N., & Islam, R. (2016). A survey of anomaly detection techniques in the financial domain. Future Generation Computer Systems, 55, 278-288. https://doi.org/10.1016/j.future.2015.07.002.
Šustrová, T. (2016). A suitable artificial intelligence model for inventory level optimization. Trends in Economics and Management, 10(24), 48-55. https://doi.org/10.13164/trends.2016.24.48.
Elliott, A., Cucuringu, M., Luaces, M. M., Reidy, P., & Reinert, G. (2019). Anomaly detection in networks with application to financial transaction networks. arXiv preprint arXiv:1901.00402. https://doi.org/10.48550/arXiv.1901.00402.
Grimes, C., Sun, J., & Wang, P. (2023). Advances in deep learning-based anomaly detection for financial fraud. Expert Systems with Applications, 212, 119305. https://doi.org/10.1016/j.eswa.2023.119305.
Haque, S. A., Rahman, M., & Aziz, S. M. (2015). Sensor anomaly detection in wireless sensor networks for healthcare. Sensors, 15(4), 8764-8786. https://doi.org/10.3390/s150408764.
Hilal, W., Gadsden, S. A., & Yawney, J. (2022). Financial fraud: A review of anomaly detection techniques and recent advances. Expert Systems with Applications, 193, 116429. https://doi.org/10.1016/j.eswa.2021.116429.
Jordan, M. I., & Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245), 255-260. https://doi.org/10.1126/science.aaa8415.
Li, X., & Kumar, P. (2023). Clustering-based anomaly detection in supply chain data: A hybrid model approach. International Journal of Computer Science Studies, 7(2), 112-126. https://doi.org/10.5555/ijcss.2023.00702.
Pereira, J., & Silveira, M. (2019). Learning representations from healthcare time series data for unsupervised anomaly detection. Proceedings of the IEEE International Conference on Big Data and Smart Computing (BigComp), Kyoto, Japan, 1-7. https://doi.org/10.1109/BIGCOMP.2019.8679201.
Pinto, S. O., & Sobreiro, V. A. (2022). Literature review: Anomaly detection approaches on digital business financial systems. Digital Business, 2, 100038. https://doi.org/10.1016/j.digbus.2022.100038.
Priya, K., & Ramanathan, P. (2022). Supervised learning-based transaction anomaly detection in retail banking. International Journal of Computer Science Studies, 6(4), 89-102. https://doi.org/10.5555/ijcss.2022.00604.
Sabic, E., Keeley, D., Henderson, B., & Nannemann, S. (2021). Healthcare and anomaly detection: Using machine learning to predict anomalies in heart rate data. AI & Society, 36, 149-158. https://doi.org/10.1007/s00146-020-01017-w.
Schütte, R. (2017). Information systems for retail companies. In Proceedings of the 29th International Conference on Advanced Information Systems Engineering (CAiSE), 13-25. https://doi.org/10.1007/978-3-319-59536-8_2.
Thakur, S., & Singh, V. (2022). Anomaly detection in logistics data using hybrid machine learning models. International Journal of Computer Science Studies, 6(3), 54-67. https://doi.org/10.5555/ijcss.2022.00603.
Ukil, A., Bandyopadhyay, S., Puri, C., & Pal, A. (2016). IoT healthcare analytics: The importance of anomaly detection. Proceedings of the 2016 IEEE 30th International Conference on Advanced Information Networking and Applications (AINA), 994-997. https://doi.org/10.1109/AINA.2016.131.
Zipfel, J., Verworner, F., Fischer, M., Wieland, U., Kraus, M., & Zschech, P. (2023). Anomaly detection for industrial quality assurance: A comparative evaluation of unsupervised deep learning models. Computers & Industrial Engineering, 177, 109045. https://doi.org/10.1016/j.cie.2022.109045.
Mr. Kailash Thiyagarajan
Independent Researcher, Austin, TX, 78641 - United States of America
Dr. Sivasai Nadella
Independent Researcher, Memphis, TN, 38125 - United States of America
sivasai.nadella@ieee.org


CREATE AUTHOR ACCOUNT
 
LAUNCH YOUR SPECIAL ISSUE
View all special issues >>
 
PUBLICATION VIDEOS