David Enke

The use of data mining and neural networks for forecasting stock market returns

It has been widely accepted by many studies that non-linearity exists in the financial markets and that neural networks can be effectively used to uncover this relationship. Unfortunately, many of these studies fail to consider alternative forecasting techniques, the relevance of input variables, or the performance of the models when using different trading strategies. This paper introduces an information gain technique used in machine learning for data mining to evaluate the predictive relationships of numerous financial and economic variables. Neural network models for level estimation and classification are then examined for their ability to provide an effective forecast of future values. A cross-validation technique is also employed to improve the generalization ability of several models. The results show that the trading strategies guided by the classification models generate higher risk-adjusted profits than the buy-and-hold strategy, as well as those guided by the level-estimation based forecasts of the neural network and linear regression models.

The adaptive selection of financial and economic variables for use with artificial neural networks

Abstract It has been widely accepted that predicting stock returns is not a simple task since many market factors are involved and their structural relationships are not perfectly linear. Recently, a promising data mining technique in machine learning has been proposed to uncover the predictive relationships of numerous financial and economic variables. Inspired by the fact that the determinant between these variables and their interrelationships over stock returns changes over time, we explore this issue further by using data mining to uncover the recent relevant variables with the greatest predictive ability. The objective is to examine whether using the recent relevant variables leads to additional improvements in stock return forecasting. Given evidence of non-linearity in the financial market, the resulting variables are then provided to neural networks, including probabilistic and feed-forward neural networks, for predicting the directions of future excess stock return. The results show that redeveloped neural network models that use the recent relevant variables generate higher profits with lower risks than the buy-and-hold strategy, conventional linear regression, and the random walk model, as well as the neural network models that use constant relevant variables.

Intelligent technical analysis based equivolume charting for stock trading using neural networks

It has been long recognized that trading volume provides valuable information for understanding stock price movement. As such, equivolume charting was developed to consider how stocks appear to move in a volume frame of reference as opposed to a time frame of reference. Two technical indicators, namely the volume adjusted moving average (VAMA) and the ease of movement (EMV) indicator, are developed from equivolume charting. This paper explores the profitability of stock trading by using a neural network model developed to assist the trading decisions of the VAMA and EMV. The generalized regression neural network (GRNN) is chosen and utilized on past S&P 500 index data. For the VAMA, the GRNN is used to predict the future stock prices, as well as the future width size of the equivolume boxes typically utilized on an equivolume chart, for calculating the future value of the VAMA. For the EMV, the GRNN is also used to predict the future value of the EMV. The idea is to further exploit the equivolume potential by using a forecasting system to predict the future equivolume measurements, allowing investors to enter or exit trades earlier. The results show that the stock trading using the neural network with the VAMA and EMV outperforms the results of stock trading generated from the VAMA and EMV without neural network assistance, the simple moving averages (MA) in isolation, and the buy-and-hold trading strategy.

Forecasting daily stock market return using dimensionality reduction

A data mining procedure to forecast daily stock market return is proposed.The raw data includes 60 financial and economic features over a 10-year period.Combining ANNs with PCA gives slightly higher classification accuracy.Combining ANNs with PCA provides significantly higher risk-adjusted profits. In financial markets, it is both important and challenging to forecast the daily direction of the stock market return. Among the few studies that focus on predicting daily stock market returns, the data mining procedures utilized are either incomplete or inefficient, especially when a large amount of features are involved. This paper presents a complete and efficient data mining process to forecast the daily direction of the S&P 500 Index ETF (SPY) return based on 60 financial and economic features. Three mature dimensionality reduction techniques, including principal component analysis (PCA), fuzzy robust principal component analysis (FRPCA), and kernel-based principal component analysis (KPCA) are applied to the whole data set to simplify and rearrange the original data structure. Corresponding to different levels of the dimensionality reduction, twelve new data sets are generated from the entire cleaned data using each of the three different dimensionality reduction methods. Artificial neural networks (ANNs) are then used with the thirty-six transformed data sets for classification to forecast the daily direction of future market returns. Moreover, the three different dimensionality reduction methods are compared with respect to the natural data set. A group of hypothesis tests are then performed over the classification and simulation results to show that combining the ANNs with the PCA gives slightly higher classification accuracy than the other two combinations, and that the trading strategies guided by the comprehensive classification mining procedures based on PCA and ANNs gain significantly higher risk-adjusted profits than the comparison benchmarks, while also being slightly higher than those strategies guided by the forecasts based on the FRPCA and KPCA models.

A hybrid stock trading system for intelligent technical analysis-based equivolume charting

This paper presents the use of an intelligent hybrid stock trading system that integrates neural networks, fuzzy logic, and genetic algorithms techniques to increase the efficiency of stock trading when using a volume adjusted moving average (VAMA), a technical indicator developed from equivolume charting. For this research, a neuro-fuzzy-based genetic algorithm (NF-GA) system utilizing a VAMA membership function is introduced. The results show that the intelligent hybrid system takes advantage of the synergy among these different techniques to intelligently generate more optimal trading decisions for the VAMA, allowing investors to make better stock trading decisions.

Stock Market Prediction with Multiple Regression, Fuzzy Type-2 Clustering and Neural Networks

Abstract Stock market forecasting research offers many challenges and opportunities, with the forecasting of individual stocks or indexes focusing on forecasting either the level (value) of future market prices, or the direction of market price movement. A three-stage stock market prediction system is introduced in this article. In the first phase, Multiple Regression Analysis is applied to define the economic and financial variables which have a strong relationship with the output. In the second phase, Differential Evolution-based type-2 Fuzzy Clustering is implemented to create a prediction model. For the third phase, a Fuzzy type-2 Neural Network is used to perform the reasoning for future stock price prediction. The results of the network simulation show that the suggested model outperforms traditional models for forecasting stock market prices.

An adaptive stock index trading decision support system

The system provides an automated and adaptive model selection process.The system predicts the stock price direction, rather than the forecasted level.Particle swarm optimization is used to reduce computation time.Denoising is used to deal with stock market volatility. Predicting the direction and movement of stock index prices is difficult, often leading to excessive trading, transaction costs, and missed opportunities. Often traders need a systematic method to not only spot trading opportunities, but to also provide a consistent approach, thereby minimizing trading errors and costs. While mechanical trading systems exist, they are usually designed for a specific stock, stock index, or other financial asset, and are often highly dependent on preselected inputs and model parameters that are expected to continue providing trading information well after the initial training or back-tested model development period. The following research leads to a detailed trading model that provides a more effective and intelligent way for recognizing trading signals and assisting investors with trading decisions by utilizing a system that adapts both the inputs and the prediction model based on the desired output. To illustrate the adaptive approach, multiple inputs and modeling techniques are utilized, including neural networks, particle swarm optimization, and denoising. Simulations with stock indexes illustrate how traders can generate higher returns using the developed adaptive decision support system model. The benefits of adding adaptive and intelligent decision making to forecasts are also discussed.

Volatility Forecasting Using a Hybrid GJR-GARCH Neural Network Model

Abstract Volatility forecasting in the financial markets, along with the development of financial models, is important in the areas of risk management and asset pricing, among others. Previous testing has shown that asymmetric GARCH models outperform other GARCH family models with regard to volatility prediction. Utilizing this information, three popular Neural Network models (Feed-Forward with Back Propagation, Generalized Regression, and Radial Basis Function) are implemented to help improve the performance of the GJR(1,1) method for estimating volatility over the next forty-four trading days. During training and testing, four different economic cycles have been considered between 1997-2011 to represent real and contemporary periods of market calm and crisis. In addition to stress testing for different neural network architectures to assess their performance under various turmoil and normal situations in the U.S. market, their synergy along with another econometric model is also accessed.

Developing a rule change trading system for the futures market using rough set analysis

This study proposes a unique rule change trading system for the futures market.Rough set analysis is adopted for generating trading rules.A genetic algorithm is used to optimize the thresholds for buying and selling signals.To verify the proposed system, a sliding window method is applied. Many technical indicators have been selected as input variables in order to develop an automated trading system that determines buying and selling trading decision using optimal trading rules within the futures market. However, optimal technical trading rules alone may not be sufficient for real-world application given the endlessly changing futures market. In this study, a rule change trading system (RCTS) that consists of numerous trading rules generated using rough set analysis is developed in order to cover diverse market conditions. To change the trading rules, a rule change mechanism based on previous trading results is proposed. Simultaneously, a genetic algorithm is employed with the objective function of maximizing the payoff ratio to determine the thresholds of market timing for both buying and selling in the futures market. An empirical study of the proposed system was conducted in the Korea Composite Stock Price Index 200 (KOSPI 200) futures market. The proposed trading system yields profitable results as compared to both the buy-and-hold strategy, and a system not utilizing a genetic algorithm for maximizing the payoff ratio.

An expert advisory system for the ISO 9001 quality system

Abstract The ISO 9000 quality management system has been widely accepted and adapted as a national standard by most industrial countries. Despite its high popularity and the urgent demand from customers to implement ISO 9000, some major concerns for those organizations that are seeking registration to ISO 9000 include the expensive cost and the lengthy time to implement. The purpose of this paper is to describe an expert advisory system for ISO 9001 implementation by using an expert system shell called Visual Rules Studio. This expert advisory system integrated the ISO 9001 quality system guidelines and an evaluation approach based on the Malcolm Baldrige National Quality Award (MBNQA) criteria into a knowledge-based expert system. By identifying the critical ISO elements and comparing the companys current quality performance with ISO standards, this advisory system provides assessment results and implementation suggestions to the organization. The advisory system has been validated by a group of quality professionals. The following contains a description of the system and a discussion of the validation results. Limitations of the system and recommendations for future research are also discussed.