EXPLAINABLE MACHINE LEARNING FOR FINANCIAL ANALYSIS
Abstract
Technical analysis plays a vital role in the dynamic world of stock trading by helping traders identify patterns and trends in market prices. However, interpreting these patterns can be complicated, especially for novice traders, due to the complexity of charts and indicators involved. This research introduces a user-friendly tool aimed at making technical analysis more accessible. It provides a streamlined interface for analysing and forecasting stock trends, catering to users of varying expertise. Most existing trading platforms either lack predictive features or operate as opaque 'black-box' systems, which can deter beginner users. To address this, the research developed a solution that simplifies financial analysis and enhances clarity. This tool stands out by reducing reliance on complex visuals, improving user understanding of financial indicators, and explaining how they influence market predictions. A unique feature of the tool is its use of Explainable Artificial Intelligence (XAI), which provides transparency and builds user trust. Feedback from user testing was positive, with participants highlighting the toolβs clarity and interactivity as valuable for making informed investment decisions.
Zenodo DOI:- https://doi.org/10.5281/zenodo.16566789Keywords
References
Most read articles by the same author(s)
- Olabayoji Oluwatofunmi Oladepo., Explainable Artificial Intelligence in Socio-Technical Contexts: Addressing Bias, Trust, and Interpretability for Responsible Deployment , International Journal of Advanced Artificial Intelligence Research: Vol. 2 No. 09 (2025): Volume 02 Issue 09
Similar Articles
- Nadezhda Shiroglazova, Dynamic Operator Allocation for Conversational AI Voice-Calling Systems , International Journal of Advanced Artificial Intelligence Research: Vol. 3 No. 07 (2026): Volume 03 Issue 07
You may also start an advanced similarity search for this article.