Copyright © 2025 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{180766,
        author = {Meshram Aniket and Verma Prem and Manchalwar Shreerup and Rijul Belowo and Prof. N. H. Deshpande},
        title = {Startup Profitability Prediction using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {2682-2687},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180766},
        abstract = {An inventive tool created to improve investment decision-making in the startup ecosystem is the ML-Based Startup Profit Predictor. This program uses machine learning to anticipate a startup’s future profitability by analyzing a large data-set of investor profiles and startup information. Entrepreneurs may refine their tactics based on insights supported by data, and investors can utilize similar forecasts to optimize their portfolios and reduce risks. This application helps investors and entrepreneurs by providing a data-driven approach to navigating the ever-changing world of startup investing. The goal of this effort is to develop a machine learning predictive model that can be used to predict a company’s success. In recent years, numerous initiatives akin to this have been made. Many of those tests yielded encouraging findings; they were frequently carried out using data collected from multiple sources. Nevertheless, we discovered that they were frequently markedly skewed because they used data that contained details about the information that directly resulted from a business’s success (or failure). This kind of thinking is a prime illustration of the look ahead bias. It produces extremely optimistic test findings, but any attempt to apply this method in a real-world setting could have disastrous repercussions. Our studies were planned such that they would not the disclosure to the training set of any information that was not known at the time of choice.},
        keywords = {},
        month = {June},
        }