Fuzzy Expert System for Stock Portfolio Selection: An Application to Bombay Stock Exchange (original) (raw)
Related papers
Stock portfolio selection using Dempster-Shafer evidence theory
Markowitz's return-risk model for stock portfolio selection is based on the historical return data of assets. In addition to the effect of historical return, there are many other critical factors which directly or indirectly influence the stock market. We use the fuzzy Delphi method to identify the critical factors initially. Factors having lower correlation coefficients are finally considered for further consideration. The critical factors and historical data are used to apply Dempster-Shafer evidence theory to rank the stocks. Then, a portfolio selection model that prefers stocks with higher rank is proposed. Illustration is done using stocks under Bombay Stock Exchange (BSE). Simulation is done by Ant Colony Optimization. The performance of the outcome is found satisfactory when compared with recent performance of the assets.
Decision making using fuzzy logic for stock trading
Information Technology (ITSim), 2010
This paper presents the Fuzzy IF-THEN Rules for a decision support system in stock trading. The three following linguistic variables will be the input for the rule. There are; view from the expert, earning-per-share and price to earnings ratio. The purpose of this rule is to assist the investors during making a decision on their share. The investors need to make a right decision to gain a high profit in stock trading. Stock market is one of complex environment. Therefore by using this Artificial Intelligence (AI) application which is Fuzzy Logic (FL) can make it simpler as well as gives benefits to investors. Most of the earlier research works show that FL can work within stocks environment. All the fuzzy rules have been evaluated by using Fuzzy Inference System in MATLAB.
Development of Quantitative Investment Model Based on Selecting Stocks with AI
2020
The objectivity and rapidity of quantitative investment are more and more loved by investors. The stock market is a complex nonlinear system with low signal-to-noise ratio, and artificial intelligence has been proved to be a powerful tool for modeling fuzzy nonlinear data. This paper analyzes the common algorithms of artificial intelligence, gives the idea and process of the development of quantitative investment model based on artificial intelligence, which provides references for the relevant researchers.
Fuzzy Rule Based System to Characterize the Decision Making Process in Share Market
This research work will help the customer for decision making in share market, based on fuzzy rule based system. Past performance data could be used to overcome uncertainty , vagueness and imprecision of share market. Six factors which are affecting the share prices are Market Growth, Monson Policy/Political Foreign Investment, Ratio Analysis and Agent Activity are very helpful to take market share price decision. Technical and fundamental approaches are used in parallel to estimate short-term and long-term return and risk. The customer will more secure to take risk at time of share trading, Fuzzy Logic framework is developed to carry out the required analysis for arriving at the governance rating of the firms.
Intelligent techniques in stock analysis
2001
Abstract. The paper presents computer system, named Stock Market Electronic Expert (SMEE), for Stock Market Analysis. It is developed as friendly, useful and credible computer program giving advises concerning investment policy on Stock Market. Fundamental and technical analysis are made automatically, and-on the base of obtained partial results-system produces evaluation of companies' attractiveness as well as comments and suggestions for users in text format.
Fuzzy clustering rule-based expert system for stock price movement prediction
Through the years, the ability to predict the future trend of financial time series has drawn serious attention from both researchers and practitioners aiming to have better investment decisions. In this paper a fuzzy rule-based expert system is developed for predicting stock price movement. The importance of the proposed expert system is that it would be applicable for stock market's speculators and traders' daily transactions. For the experiment and in order to demonstrate the effectiveness of the model, the stock price of Apple Company is used as a sample data set.
Advances in Operations Research
This paper presents a stock selection approach assisted by fuzzy procedures. In this approach, stocks are classified into groups according to business types. Within each group, the stocks are screened and then ranked according to their investment weight obtained from fuzzy quantitative analysis. Groups were also ranked according to their group weight obtained from fuzzy analytic hierarchy process (FAHP) and technique for order preference by similarity to ideal solution method (TOPSIS). The overall weight for each stock was then derived from both of these weights and used for selecting a stock into the portfolio. As a demonstration, our analysis procedures were applied to a test set of data.
Optimization of Portfolio Using Fuzzy Selection
BAREKENG: Jurnal Ilmu Matematika dan Terapan
The problem of portfolio optimization concerns the allocation of the investor’s wealth between several security alternatives so that the maximum profit can be obtained. One of the methods used is Fuzzy Portfolio Selection to understand it better. This method separates the objective function of return and the objective function of risk to determine the limit of the membership function that will be used. The goal of this study is to understand the application of the Fuzzy Portfolio Selection method over shares that have been chosen on a portfolio optimization problem, understand return and risk, and understand the budget proportion of each claim. The subject of this study is the shares of 20 companies included in Bursa Efek Indonesia from 1 January 2021 until 1 January 2022. The result of this study shows that from 20 shares, there are 10 shares that is suitable in the forming of optimal portfolio, those are ADRO (0%), ANTM (43.3%), ASII (0%), BBCA (0%), BBRI (0%), BBTN (0%), BRPT (0%...
A stock selection strategy using fuzzy neural networks
Computer Science in Economics and Management, 1991
This paper describes, from a general system-design perspective, an artificial neural network (ANN) approach to a stock selection strategy. The paper suggests a concept of neural gates which are similar to the processing elements in ANN, but generalized into handling various types of information such as fuzzy logic, probabilistic and Boolean information together. Forecasting of stock market returns, assessing of country risk and rating of stocks based on fuzzy rules, probabilistic and Boolean data can be done using the proposed neural gates. Fuzzy logic is known to be useful for decisionmaking where there is a great deal of uncertainty as well as vague phenomena, but lacks the learning capability; on the other hand, neural networks are useful in constructing an adaptive system which can learn from historical data, but are not able to process ambiguous rules and probabilistic data sets. This paper describes how these problems can be solved using the proposed neural gates.
Stock Market Prediction and Investment Portfolio Selection Using Computational Approach
Stock Market is considered as one of the fundamental pillars of national economy, as the important purpose of stock market in the economy is to raise capital and also to transfer funds to the most profitable opportunities, Therefore Predicting Stock Price, Predicting Timing and Selection of Portfolio are considered as several extremely complex situations in stock market. because, they are affected by many interrelated economic, social, political and even psychological factors at both local and global levels and all these factors are interrelated with each other in a very critical manner, These makes use of Mathematical Approaches & Soft Computing techniques combinely. These techniques can be used to select scripts in the portfolio and predict stock price or trading signal automatically with acceptable precision in order to retrieve information that could help to suggest investors on whether to Buy, Hold or Sell. This paper reviews the literature concerning different computational methods, such as linear programming, goal programming, data mining and soft computing strategies with an emphasis on the historical perspective and from many other resources such as, web sources, research papers, articles etc. The various fundamental, technical, economical and political factors of Indian Stock Market are considered.