Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{201259,
        author = {Aman Husain and Rohan Sonawane and Pooja Jadhav and Om Lotke and Mrs.Samiksha Gawali and Dr.Umesh Pawar},
        title = {Intelligent personal finance advisor with generative insights (Moneyy Mantra).},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {2997-3005},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201259},
        abstract = {Intelligent Financial Advisors (IFAs) in online financial apps have made personal investing more exciting by giving users the right and high-quality portfolios. Finding potential clients is a very important job for IFAs in the real world. This means finding people who are willing to buy the portfolios. So, it's important to quickly get useful information from different traits of users and then guess how likely they are to buy something. However, two major issues that come up in real life make this prediction task hard: sample selection bias and data sparsity. In this study, we formalize a potential conversion relationship, specifically user activated user client, and decompose this relationship into three interconnected tasks. Then, we suggest a Multitask Feature Extraction Model (MFEM) that can use useful information from these related tasks and learn them all at once, solving both problems at the same time. We also create a two-stage feature selection algorithm that can quickly and accurately pick out the most important user features from a very large number of user feature fields. In the end, we do a lot of tests on a real-world dataset that a well-known fintech bank gave us. The experimental results show clearly that MFEM works.},
        keywords = {Intelligent Financial Advisor (IFA); potential client identification; Multitask Learning (MTL); feature selection.},
        month = {May},
        }