The egyptian stock market return prediction: a genetic programming approach (original) (raw)

Discovering the classification rules for Egyptian stock market using genetic programming

2003

Applications of learning algorithms in knowledge discovery are promising and relevant area of research. It is offering new possibilities and benefits in real-world applications, helping us understand better mechanisms of our own methods of knowledge acquisition. Genetic programming (GP) possess certain advantages that make it suitable for discovering the classification rule for data mining applications, such as convenient structure for rule generation. This paper, intended to discover classification rules for the Egyptian stock market return by applying GP. Since the Egyptian stock market return data have a large number of specific properties that together makes the generalized classification rules unusual. The process behaves very much like a random-walk process and regime shift in the sense that the underlying process is time varying. These reasons cause greats problems for the traditional classification algorithms. Experiments presenting a preliminary result to demonstrate the capability of GP to mine accurate classification rules suitable for prediction, comparable to traditional machine learning algorithms i.e., C4.5

Genetic Algorithms for Predicting the Egyptian Stock Market

2005 International Conference on Information and Communication Technology, 2005

The purpose of this paper is to discover a semi-optimal set of trading rules and to investigate its effectiveness as applied to Egyptian Stocks. The aim is to mix different categories of technical trading rules and let an automatic evolution process decide which rules are to be used for particular time series. This difficult task can be achieved by using Genetic Algorithms (GA's), they permit the creation of artificial experts taking their decisions from an optimal subset of the a given set of trading rules. The GA's based on the survival of the fittest, do not guarantee a global optimum but they are known to constitute an effective approach in optimizing non-linear functions. Selected Liquid Stocks are tested and GA Trading rules were compared with other Conventional and well known Technical Analysis Rules. The Proposed GA system showed clear better average profit and in the same High Sharpe ratio, which indicates not only good profitability but also better risk-reward trade-off.

A Genetic Programming Model for S&P 500 Stock Market Prediction

International Journal of Control and Automation, 2013

The stock market is considered one of the most standard investments due to its high revenues. Stock market investment can be risky due to its unpredictable activities. That is why, there is an urgent need to develop intelligent models to predict the for stock market index to help managing the economic activities. In the literature, several models have been proposed to give either shortterm or long-term prediction, but what makes these models supersede the others is the accuracy of their prediction. In this paper, a prediction model for the Standards & Poors 500 (S&P500) index is proposed based Genetic Programming (GP). The experiments and analysis conducted in this research show some unique advantages of using GP over other soft computing techniques in stock market modeling. Such advantages include generating mathematical models, which are simple to evaluate and having powerful variable selection mechanism that identifies significant variables.

Genetic Programming for Financial Time Series Prediction

Lecture Notes in Computer Science, 2001

This paper describes an application of genetic programming to forecasting financial markets that allowed the authors to rank first in a competition organized within the CEC2000 on "Dow Jones Prediction". The approach is substantially driven by the rules of that competition, and is characterized by individuals being made up of multiple GP expressions and specific genetic operators.

A Genetic Learning Algorithm Applied to Financial Forecasting

IFAC Proceedings Volumes, 1999

An introduction i~made about financial theory and several financial forecasting techniques, putting SOITIe elnphasis in the ne\-\' role of non-linear techniques. A supervised inductive tnachine learning approach to the problem of representing, identifying and classjfying patterns in the evolution of stock prices js presented. A genetic learning algorilhm is described to deal with such a machine learning problem. Preliminary results allowing conclusions about the system's good learning and generalisation capabilities and consequent forecasting performances are shown.

FINANCIAL FORECASTING USING GENETIC ALGORITHMS

Over the last decade, genetic algorithms (GAs) have been extensively used as search and optimization tools in various problem domains, including Sciences, Commerce, and Engineering. The generation of profitable trading rules for stock market investments is a difficult task but admirable problem. In this paper, I first explained about basic functions involved in GAs with examples, later I prepare a model for financial forecasting using Genetic Algorithms. The trading rules would yield highest return over a certain time period using historical data.

Stock market modeling using genetic programming ensembles

2006

The use of intelligent systems for stock market predictions has been widely established. This chapter introduces two Genetic Programming (GP) techniques: Multi-Expression Programming (MEP) and Linear Genetic Programming (LGP) for the prediction of two stock indices. The performance is then compared with an artificial neural network trained using Levenberg-Marquardt algorithm and Takagi-Sugeno neuro-fuzzy model.

Genetic programming application to generate technical trading rules in stock markets

International Journal of Reasoning-based Intelligent Systems, 2010

Technical trading rules can be generated from historical data for decision making in stock trading. In this study, genetic programming (GP) as an evolutionary algorithm has been applied to automatically generate such technical trading rules on individual stocks. In order to obtain more realistic trading rules, we have included transaction costs, dividends and splits in our GP model. Our model has been applied for nine Iranian companies listed on different activity sectors of Tehran Stock Exchange (TSE). Our results show that this model could generate profitable trading rules in comparison with buy and hold strategy for companies having frequent trading in the market. Also, the effect of the above mentioned parameters on trading rule's profitability are evaluated using three separate models.

Estimating time series predictability using genetic programming

A new method that quantifies the genetic programming predictability of a stock's price is presented. This new method overcomes resolution and stationarity problems presented in previous approaches. A comparison, showing the advantages of the new method, is made, between the approaches, on four time series.

The importance of simplicity and validation in genetic programming for data mining in financial data

Proceedings of the joint GECCO-99 and AAAI-99 …, 1999

A genetic programming system for data mining trading rules out of past foreign exchange data is described. The system is tested on real data from the dollar/yen and dollar/DM markets, and shown to produce considerable excess returns in the dollar/yen market. Design issues relating to potential rule complexity and validation regimes are explored empirically. Keeping potential rules as simple as possible is shown to be the most important component of success. Validation issues are more complicated. Inspection of fitness on a validation set is used to cutoff search in hopes of avoiding overfitting. Additional attempts to use the validation set to improve performance are shown to be ineffective in the standard framework. An examination of correlations between performance on the validation set and on the test set leads to an understanding of how such measures can be marginally benificial; unfortunately, this suggests that further attemps to improve performance through validation will be difficult.