Optimizing Machine Learning for Product Category Prediction in Digital Wallet Transactions: A Case Study of Feature-Driven Performance
- Title
- Optimizing Machine Learning for Product Category Prediction in Digital Wallet Transactions: A Case Study of Feature-Driven Performance
- Creator
- Ruben, V. Muthu; VijayaKumar, R.; Kumar, T. K. Sateesh
- Description
- The Digital Wallet transactions is one of the rapid phenomena in the application of technology. There were various studies which explored to application and sophistication of this digital wallet transactions. Based on the secondary data, the researcher developed a model for classifications using machine learning algorithms in Jupyter notebook (Python IDE). In the current study the performance of the machine learning model for classification is conducted on product categories in digital wallet transaction using many features such as product amount transaction fees cashback and encode categorical variables merchant name product name and payment methods. The test results of the classification model show and oral accuracy of the model at 92% with Precision recall and F1 scores averaging up to 0.92. It is noticeable that some of the features such as gas bill electricity bill showed weaker performance suggesting the need for further engineering and model tuning. This provide the deep understanding on how the transactions related features contribute to predicting the accuracy and highlights the potential for improving classification models for financial technology and its applications. The study also provides future directions and implications for the model refinement focusing on improving miss classification in categories. The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
- Source
- Studies in Systems, Decision and Control;Volume;584;pp.115-121
- Date
- 01-01-2025
- Publisher
- Springer Science and Business Media Deutschland GmbH
- Subject
- Classification model; Digital wallet transactions; Feature engineering; Financial technology; Machine learning; Precision and recall; Product category prediction; Transaction features
- Coverage
- Ruben V.M., Christ University (Deemed to Be University), Bangalore, India; VijayaKumar R., Kristu Jayanti College (Autonomous), Bangalore, India; Kumar T.K.S., Kristu Jayanti College (Autonomous), Bangalore, India
- Rights
- Restricted Access; Hardcopy may be available in the library
- Relation
- ISSN: 21984182;
- Format
- online
- Language
- English
- Type
- Book chapter
Collection
Citation
Ruben, V. Muthu; VijayaKumar, R.; Kumar, T. K. Sateesh, “Optimizing Machine Learning for Product Category Prediction in Digital Wallet Transactions: A Case Study of Feature-Driven Performance,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 19, 2026, https://archives.christuniversity.in/items/show/24002.