Power of Predictive Analytics for Prediction based on Patterns for Stock Market

Power of Predictive Analytics for Prediction based on Patterns for Stock Market

Assumptions of Movie PI
1. Mathematics is the language of nature. 2. Everything around us can be represented and understood through numbers. 3. If you graph the numbers of any system, patterns emerge. Therefore: There are patterns everywhere in nature. So, what about the stock market? The universe of numbers that represents the global economy. Millions of human hands at work, billions of minds. A vast network, screaming with life. An organism. A natural organism. My hypothesis: Within the stock market, there is a pattern as well. Right in front of me. Hiding behind the numbers. Always has been.

Back testing findings for Nifty 50 Stocks totally 831 years of data.

1. Out of 831 years of data (Jan to Dec for each year for Nifty 50 stocks), no pattern for 170 years (includes 50 records of 2022 as 2023 is not yet over so can not confirm precisely for 2022)
2. Correct Prediction in terms of direction, on whether stock would go on higher side or lower side 381 records (57.64%), Out of 381 records 336 records have positive prediction and 45 records have negative predictions).
3. Incorrect prediction in terms of direction on whether stock would go on higher side or lower side 280 records (42.36%)
3. Only previous year records considered e.g. For validating a stock for year 2020, all records up to 2019 considered
4. The prediction percentage generated was average percentage of all the records of the past that had matching pattern.
5. Average deviation of percentage of all the correctly predicted records 18.40% (Prediction percent on higher side compared to actual percentage)
6. If instead of Average percentage, if maximum percentage value for positive prediction and minimum percentage value for negative predictions is considered, then prediction accuracy increases to 386 records (333 positive and 53 negative predictions) with 58.40% accuracy. However it also increases the deviation percentage from 18.40% 128%
7. One can club the prediction data with price momentum and Relative strength investment strategies for entering and exiting a stock.
8. Yearly prediction can be regenerated every month with pair of Jan to Dec, Feb to Jan...etc