Rafiq, Atif, Javed, Noman, Raja, Muhammad Adil, Hanif, Ambreen and Ryan, Conor (2020) Devising technical trading rules for Pakistan stock exchange using genetic programming. In: 3rd International Conference on Intelligent Sustainable Systems ICISS 2020, 2020-12-03 - 2020-12-05, Hotel Arcadia. (In Press)
Full text not available from this repository.Abstract
The efficient market hypothesis (EMH) suggests that a stock market behaves like a random walk; if so, then forecasting the trends and developing profitable trading strategies would not possible. On the other hand, quantitative traders exploit short term behavior of the market using technical analysis. In particular, due to progress in computational intelligence, hybrid approaches based on machine learning and technical analysis, profit margin from stock investing have increased when compared to traditional buy and hold strategies.Technical analysis generally uses combinations of technical indicators, such as moving average, etc., to build rules to control the buying and selling of stocks. The profit made from investing is highly dependent on the timing of the investment decisions suggested by such rules. Changing the combination of or tweaking the parameters of technical indicators can change the rules and hence the profitability of the strategy. Moreover, it is computationally expensive to exhaustively try all the possible permutations of these indicators. Our approach relies on genetic programming (GP) to efficiently explore the search space and evolve trading rules capable of generating profits given unseen data. Instead of relying on traditional train-test split, walk forward validation is used. The approach is tested on 8 stocks of Pakistan stock exchange (PSX). Trading rules evolved using our approach outperform buy and hold approach when tested over the historical data of the PSX. Index Terms—Trading Rules, Profit Maximization, Genetic Programming, Pakistan Stock Exchange (PSX)
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Divisions: | CPNSS |
| Date Deposited: | 12 Nov 2020 14:30 |
| Last Modified: | 12 Nov 2020 14:31 |
| URI: | http://eprints.lse.ac.uk/id/eprint/107432 |
Actions (login required)
 |
View Item |
