An expdriment result based on adaptive neuro fuzzy inference system for stock price predict on

The acquisition of high-frequency data in real times has developed new fields like neuro-fuzzy systems for forcasting problems, renewing also the interest in the forcasting of financial and stock market indexes. In this paper, we present an experiment result based on Adaptive Neuro-Fuzzy Inference System with a new computing procedure for stock price prediction.
Nội dung trích xuất từ tài liệu:
An expdriment result based on adaptive neuro fuzzy inference system for stock price predict onJournal of Computer Science and Cybernetics, V.27, N.1 (2011), 51–60AN EXPDRIMENT RESULT BASED ON ADAPTIVE NEURO-FUZZYINFERENCE SYSTEM FOR STOCK PRICE PREDICT ONBUI CONG CUONG1 , PHAM VAN CHIEN21 Institute of2MathematicsHanoi University of Science and Technology’’´´ .´`T´m t˘t. Trong nh˜.ng n˘m cuˆi thi tru.o.ng t`i ch´ thˆ gi´.i d˜ thay dˆ i nh`. su. ph´t triˆn nhiˆuoauao`aınh e o aoo .aee’`´ng tiˆn tiˆn. Nh˘ m khai th´c d˜. liˆu th`.i gian thu.c d˜ ph´t triˆn nh˜.ng l˜ vu.c m´.i nhu.´hˆ thˆe oeeaa u ea aeuoınh .o...´´’ oc´c hˆ m`. no.ron d`nh cho b`i to´n du. b´o v` nhu. vˆy l`m sˆ ng lai quan tˆm t´.i du. b´o c´c chı sˆa e oaa aa aa aoao . a a....˜’t`i ch´ v` ch´.ng kho´n. B`i b´o n`y gi´.i thiˆu mˆt thu. nghiˆm d` ng hˆ suy diˆn m`. - no.ron v´.iaınh a uaa a aoeoeueeoo....’mˆt quy tr` t´ to´n m´.i dˆ du. b´o gi´ ch´.ng kho´n.oınh ınh ao e . aa ua.Abstract. In the last years, the financial markets around the world have been modified by therapid development of advance systems. The acquisition of high-frequency data in real times hasdeveloped new fields like neuro-fuzzy systems for forcasting problems, renewing also the interest inthe forcasting of financial and stock market indexes. In this paper, we present an experiment resultbased on Adaptive Neuro-Fuzzy Inference System with a new computing procedure for stock priceprediction.1. INTRODUCTIONArtifical neural networks (ANN) have been successfully applied to a number of scientificand engineering fields in recent years, e.g. function approximation, system identification andcontrol, image processing, time series prediction and so on [1-3, 6].Time-series forcasting is an impotant research and application area. Much effort has beendevoted over the past several decades to develop and improve the time-series forecasting models. Well established time series models include : (1) linear models, e.g., moving average,exponential smoothing and the autoregressive intergrated moving average (ARIMA); (2) nonlinear models, e.g., neural network models and fuzzy system models [4-8].Neuro-fuzzy systems methods and statistical tools are different methods that can be usedto predict financial indexes. Neural networks incorporate a large number of parameters whichallows to learn the intrinsic non-linear relationship presented in time-series, enhancing theirforcasting possibilities. ANN have been successfully applied to predict important financialand market indexes, like for example, Standart and Pool 500 (SP&500). Nikei 225 Index, theNew York stock exchange composite index (NYSE index) and other.Stock price prediction has always been a subject of investors and professional analysts.Nevertheless, finding out the best time to buy or to sell has remained a very difficult taskbecause there are too many factors that influence stock. During the last decade, stocks andfuture traders have come to rely upon various types of intelligent systems. Lately, ANN andadaptive neuro-fuzzy inference system (ANFIS) have been applied to this area.52BUI CONG CUONG, PHAM VAN CHIENOther soft computing methods are also applied in the prediction of stock and these softcomputing approaches are to use quantitative inputs, like technical indexes, qualitative factors,political effects, automate stock market forcasting and trend analysis.In this paper, we will use an ANFIS with a new computing procedure for stock indexforcasting. The remainder of the paper is organized as follows: Section 2 describes the architecture of the ANFIS, Section 3 presents some learning algorithms and Section 4 is devotedto an experiment result for VN Index stock index prediction. Finally, conclusions are drawnin Section 5.2. ADAPTIVE NEURO-FUZZY INFERENCE SYSTEMAdaptive neuro-fuzzy inference system (see [3, 6 - 8]) is the most popular neuro-fuzzyconnectionist system that similar to a Sugeno type fuzzy inference systems (FIS). FIS can beefficiently used a bridge between the domain expert and a financial system. FIS works onknowledge bases that are in easily comprehensible óÀÌIF ... THENóÀÌ format. Neuro-fuzzyalgorithms are assimilarly of neural networks and FIS. These algorithms are essentially adaptive, lucid and highly flexible. As they are essentiall fuzzy inference systems embedded into aneural network, they are also robust.ANFIS architectureFigure 1 shows a sample ANFIS structure using three inputs and two labels for each input.Generally, an ANFIS structure with n inputs and m labels for each input has 5 layers. Thenode functions in each layer are of the same function family as described on figure 1.Figure 2.1. Sample ANFIS structure.Layer 1: The first layer contains n.m adaptive nodes (square nodes) with a node function:1Oi,j = µAi,j (Xi),(2.1)where Xi (0 ≤ i ≤ n − 1) is the ith input, Ai,j (0 ≤ i ≤ n − 1, 0 ≤ j ≤ m − 1) is thej th linguistic label of the ith input, such as small, normal, large, etc. is the membershipfunction of Ai,j and it specifies the degree to which the give Xi satisfies the quantifierAi,j . Usually we choose to be Generalized Bell or Gaussian membership function withAN EXPERIMENT RESULT BASED ON ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM53minimum equal to 0 and maximum equal to 1:µgbell (x) =1x − ck1+ak2bkµgaussian (x) = exp −,x − cksk2.(2.2)Therefore, (ck , ak , bk) or (ck , sk ) (0 ≤ k ≤ n.m − 1) is non-linear parameter set ofkth node. When the values of these parameter change, the shape of membership function on linguistic label Ai,j vary accordingly. In terms of calculation, we consider thati ∗ m + j = k.Layer 2: The second layer contains mn fixed nodes (circle nodes) label P. The kth (0 ≤ k ≤mn − 1) node collects the incoming signals to do the T-norm and sends the resu ...