{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/fe89a189e3b043f59ef894da66480ed3\" frameborder=\"0\" width=\"1728\" height=\"1296\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1296,"width":1728,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1296,"thumbnail_width":1728,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/fe89a189e3b043f59ef894da66480ed3-f178f0993a06c6c6.gif","duration":400.367,"title":"IPO Vista: ML Fintech IPO Performance Insights by Ayush Dudhat","description":"This Loom presents IPO Vista, a machine learning powered fintech platform that predicts IPO performance using financial data and sentiment analysis. The presenter shows the front end where users search for an IPO such as Zomato to view metrics like issue size, total subscription, quality substitution, and sentiment score with buy signals, along with leaderboards, yearly IPO releases, and distribution gains. They then outline the workflow from user dashboard to backend data sources such as exchanges and Moneycontrol, through an ML pipeline that includes data collection, preprocessing, model training and evaluation using metrics like root mean squared error and R squared, and final deployment. The Loom also covers the modular repository structure, feature engineering with indicators like MACD and RSI, model building with a bidirectional LSTM, and plans for future improvements including live market API integration and enhanced sentiment analysis."}