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{202192,
        author = {Ms. Anitta Antony and Abhinav Prateek and Doi Vasif and Anwesha Patra and Arpita Saxena},
        title = {DHANMITRA: A ML POWERED FINANCIAL ADVISOR},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {6557-6564},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202192},
        abstract = {Managing personal finances is by no means a trivial task for many individuals, either because access to professional financial planners is restricted or because financial literacy is low. The use of robo-advisors has made investment advice more widely accessible, but many of the currently available solutions rely on short questionnaires and coarse risk categories, usually resulting in generic and weakly personalized portfolios. This paper presents DhanMitra, a machine-learning–driven robo-advisory platform that elicits rich user information on income, expenditure patterns, existing assets and liabilities, and explicit financial goals and converts it into tailored savings and investment strategies. The system estimates user-specific risk preferences, designs optimized portfolios using techniques such as mean–variance optimization, and generates budget and goal-tracking recommendations that can be delivered through natural language interfaces.
We describe the overall architecture, including the data processing pipeline, risk profiling models, optimization engine, and user interface layer. Using illustrative case studies representing students, mid-career professionals, and retirees, we demonstrate how DhanMitra can adapt allocations and contribution paths to different stages of the financial life cycle. A simulation-based evaluation compares DhanMitra against simple rule-based baselines and shows that the proposed system can improve projected goal achievement and risk-adjusted returns while preserving low operational cost. The modular design allows integration of advanced language models and additional financial products, enabling DhanMitra to evolve into a comprehensive digital financial companion.},
        keywords = {Financial advisory, robo-advisor, machine learning, portfolio optimization, personalization, financial literacy, AI-driven planning.},
        month = {May},
        }