Fuzzy models for predicting time series stock price index

Journal of Energy and Natural Resource Management, 2017

Stock investment is often regarded by investors as a green opportunity that is characterized by high rewards and its attendant risk. Consequently, investors are preoccupied with analysis and prediction of the future performance of stocks, and the direction and magnitude of future changes in the stock value. In this study, the Takagi-Sugueno-Kang-Fuzzy Rule Based System (TSK-FRBS) was used to analyzed the trend of stocks using historical data gathered over a period of five months between January and May 2015. The TSK-FRBS was implemented in R. The input data is split into training and testing data for experimentation, testing and further analysis. Predictive accuracy was evaluated using the root mean squared error (RMSE) and symmetric mean absolute percentage error (SMAPE). Final results showed consistency obtained from feeding the model with the data and hence proved that patterns that allow for prediction can be deduced from the chaotic nature of the stock exchange market. Keywords adaptive-network-based inference system (ANFIS). Fuzzy, Fuzzy rule based system (FRBS), stock market, stock prediction.

Operational Research in Engineering Sciences: Theory and Applications

Decision making process in stock trading is a complex one. Stock market is a key factor of monetary markets and signs of economic growth. In some circumstances, traditional forecasting methods cannot contract with determining and sometimes data consist of uncertain and imprecise properties which are not handled by quantitative models. In order to achieve the main objective, accuracy and efficiency of time series forecasting, we move towards the fuzzy time series modeling. Fuzzy time series is different from other time series as it is represented in linguistics values rather than a numeric value. The Fuzzy set theory includes many types of membership functions. In this study, we will utilize the Fuzzy approach and trapezoidal membership function to develop the fuzzy generalized auto regression conditional heteroscedasticity (FGARCH) model by using the fuzzy least square techniques to forecasting stock exchange market prices. The experimental results show that the proposed forecasting...

Journal of Computing Research and Innovation

The stock market has always been a contentious topic in society, and it is a place where economic standards are established. The stock market is incredibly unpredictable and turbulent. This means that the shares may fluctuate for reasons that are sometimes difficult to understand. Due to this uncertainty, many investors believe the stock market as a risky investment. Therefore, having an accurate picture of future market environment is crucial to minimising losses. Forecasting is a technique of predicting the future based on the outcome of the previous data. There are a wide range of forecasting algorithms, however, this study only focuses on these two techniques: Auto Regressive Moving Average (ARIMA) model and Fuzzy Time Series (FTS) Model. The goal of this study is to evaluate and compare the effectiveness of the ARIMA model and the FTS model in predicting sample data of stock prices of Top Glove Corporation Berhad since this company is the largest glove supplier in the world ...

International Journal of Electronic Finance, 2011

A number of research had been carried out to forecast stock price based on technical indicators, which rely purely on historical stock price data. Nevertheless, their performance is not always satisfactory. In this paper, the effect of using hybrid market indicators of technical, fundamental indicators and experts opinion for stock price prediction is examined. Input variables extracted from these market hybrid indicators are fed into a fuzzy-neural network for improved accuracy of stock price prediction. The empirical results obtained with published stock data shows that the proposed model can be effective to improve accuracy of stock price prediction.

Journal of Advances in Mathematical & Computational Sciences , 2019

Stock Market can be easily seen as one of the most attractive places for investors, but it is also very complex in terms of making trading decisions. This paper presents a system which predict variable stock using historical (Open, High, Low, Close) stock prices and Fuzzy Logic. Four technical indicators were used as input variable to the fuzzy predictive system. The system programming and implementation is done using Visual Basic.Net as front end, and SQL Server as database. Data from the Nigerian Stock Exchange (NSE) was used for testing and evaluating the system. The system achieved a total of 92% accuracy in terms of making buy, hold, or sell predictions. The system when implemented can be used to draw inference in terms of making buy, hold, or sell decisions.

International Journal of Artificial Intelligence and Soft Computing, 2015

Expert Systems with Applications, 2009

Stock price predictions have always been a subject of interest for investors and professional analysts. Nevertheless, determining the best time to buy or sell a stock remains very difficult because there are many factors that may influence the stock prices. This paper establishes a novel financial time series-forecasting model by evolving and clustering fuzzy decision tree for stocks in Taiwan Stock Exchange Corporation (TSEC). This forecasting model integrates a data clustering technique, a fuzzy decision tree (FDT), and genetic algorithms (GA) to construct a decision-making system based on historical data and technical indexes. The set of historical data is divided into k sub-clusters by adopting K-means algorithm. GA is then applied to evolve the number of fuzzy terms for each input index in FDT so the forecasting accuracy of the model can be further improved. A different forecasting model will be generated for each sub-cluster. In other words, the number of fuzzy terms in each sub-cluster will be different. Hit rate is applied as a performance measure and the proposed GAFDT model has the best performance of 82% average hit rate when compared with other approaches on various stocks in TSEC.

Indian International Conference on Artificial Intelligence, 2005

This paper proposes a fuzzy logic based DSS for stock market. This system will help investors of the stock market to take the correct buy/sell/hold decisions. The results obtained from the proposed fuzzy logic model were satisfactory. A fuzzy tuning methodology was introduced to enhance the accuracy of the decisions. The tuning methodology which uses genetic algorithms is presented also in this paper. Experimental simulation using actual price data from NASDAQ index is carried out to demonstrate the power of the proposed model.

In recent years, many academy researchers have proposed several forecasting models based on technical analysis to predict models such as and . After reviewing the literature, two major drawbacks are found in past models: (1) the forecasting models based on artificial intelligence algorithms (AI), such as neural networks (NN) and genetic algorithms (GAs), produce complex and unintelligible rules; and (2) statistic forecasting models, such as time series, require some basic assumptions for variables and build forecasting models based on mathematic equations, which are not easily understandable by stock investors. In order to refine these drawbacks of past models, this paper has proposed a model, based on adaptive-network-based fuzzy inference system which uses multitechnical indicators, to predict stock price trends. Three refined processes have proposed in the hybrid model for forecasting: (1) select essential technical indicators from popular indicators by a correlation matrix; (2) use the subtractive clustering method to partition technical indicator value into linguistic values based on an data discretization method; (3) employ a fuzzy inference system (FIS) to extract rules of linguistic terms from the dataset of the technical indicators, and optimize the FIS parameters based on an adaptive network to produce forecasts. A six-year period of the TAIEX is employed as experimental database to evaluate the proposed model with a performance indicator, root mean squared error (RMSE). The experimental results have shown that the proposed model is superior to two listing models (Chen's and Yu's models).

International Journal of Computer Applications, 2015

Today, investment by purchasing stock-share constitutes the greater part of economic exchange of countries and a considerable amount of capital is exchanged through the stock markets in the whole world. But one of the most important problems is finding efficient ways to summarize and visualize the stock market data to individual or institutions useful information about the market behavior for investment decision. This research proposes an intelligent stock market forecasting system using the ability of neural network and fuzzy inference system to discover patterns in nonlinear and chaotic systems. This research with a probe in a sample of the whole population of the study involves the data financial record of BEXIMCO Ltd. which is member of Chittagong stock exchange, Bangladesh, aims at the prediction of stock price. The prediction was done by a nonlinear fuzzy-neural network model using exogenous variable of stock market.