About

About The Nifty Experiment

The Nifty Experiment is a paper-trading project: a live test of whether an AI-assisted system can make sensible day-trading decisions on Indian stocks. No real money is used. Every trade is simulated.

How it works
Each weekday, the system screens the Nifty 100 stocks. An AI model reads the day’s news and judges each stock. A fixed set of coded rules then accepts or rejects every trade plan, so the AI never has the final word. After the market closes, each accepted trade is settled using actual 5-minute price data. Results are published here and on the public dashboard at niftyexperiment.com.

Why I’m doing this
I’m Bipin, a software engineer and technical architect with 17 years of experience building backend systems. I’m new to the stock market and built this to learn it in public, including the losing days.

How AI is used on this blog
Daily result posts are drafted by the system from real trading data. I review each one and add my own comments(if required) before publishing.

Not investment advice
This is a learning project, not a recommendation. Please read the Disclaimer page.

Contact: bipin.sd@proton.me

Comments

Post a Comment

Popular posts from this blog

The Nifty Experiment: An AI Trading Bot Paper-Trading the NSE

Image
I built an AI-powered trading bot that makes simulated trades in individual stocks on India's National Stock Exchange (NSE) with fake money, and after each trading day I publish what it did: the picks, the stop-losses and the profit or loss, win or lose. It trades company shares, not index derivatives. This is The Nifty Experiment, and this is how it works. What the bot does all day The bot wakes up shortly after the market opens and works through the same routine every day. Scan. It looks across the biggest companies on the NSE and picks out the stocks that are rising on unusually strong trading activity. Read. It gathers the latest news about those stocks. An AI model reads the headlines and asks one question: is there a real, recent reason this company is in the news? Decide. A fixed set of rules, written in code, decides what, if anything, gets bought. Position sizes are small and every trade has a pre-set exit. Trade. Every trade has a stop-loss, which is the pri...
Read more

Trading bot makes no trades on 12 October 2026 as Nifty falls

Image
I built an AI-powered trading bot that executes simulated trades on the NSE with fake money, and on 12 October 2026 it did exactly what its rules told it to do: nothing. It read the news on ten rising stocks, found none that qualified, placed no trades, and finished the day with its balance unchanged at ₹100,553.90. Every stock the bot looked at # Stock Sector Up at the start Volume vs usual Headlines Decision 1 Bajaj Auto (BAJAJ-AUTO) Automobile and Auto Components +3.54% 5.96x 5 Not bought: no specific company event 2 Siemens (SIEMENS) Capital Goods +2.51% 3.34x 5 Not bought: no specific company event 3 Polycab India (POLYCAB) Capital Goods +2.47% 3.75x 5 Not bought: event still to come; news not positive 4 Tata Capital (TATACAP) Financial Services +2.46% 3.16x 5 Not bought: no specific company event 5 Hitachi Energy India (POWERINDIA) Capital Goods +2.25% 2.74x 5 Not bought: event still to come; news not positive 6 Indian...
Read more