داده کاوی برای پیش بینی مالی و تجاری: کاربرد در بازارهای منفرد و چندگانه

An alluring aspect of financial investment lies in the opportunity for respectable returns even in the absence of prediction. For instance, a portfolio tied to the S and P500 would have yielded a compound annual return in the teens over the last half century. Over the same period, a portfolio tracking the fast-growth economies of the Far East would have provided even higher returns. Previous researches in learning methods has focused on predictability based on comparative evaluation even these techniques may be employed to forecast financial markets as a prelude to intelligent trading systems. This paper explores the effect of a number of possible scenarios in this context. The alternative combinations of parameters include the selection of a learning method, whether a neural net or case based reasoning; the choice of markets, whether in one country or two; and the deployment of a passive or active trading strategy. When coupled with a forecasting system, however, a trading strategy offers the possibility for returns in excess of a passive buy-and-hold approach. In this study, we investigated the implications for portfolio management using an implicit learning technique (neural nets) and an explicit approach (CBR)

A central issue in business and economics lies in the prediction of financial variables. This is especially true for the realms of monetary policy, investment analysis, and risk management. Since the trajectory of a stock market depends on both macroeconomic and microeconomic variables, a systematic approach to knowledge discovery for stock market analysis must be able to accommodate disparate types of information. To this end, a battery of techniques from the field of data mining may be harnessed to the predictive task. A key advantage of a multistrategy approach to discovery and forecasting lies in the ability to merge data available in disparate formats. In recent years, data mining techniques such as neural networks (NN) have been applied extensively to the task of predicting financial variables. This paper explores the implications for portfolio management using an implicit learning technique (neural nets) and an explicit approach (CBR).

In recent years, data mining techniques such as NN have been applied extensively to the task of predicting financial variables. This chapter explored the implications for portfolio management using an implicit learning technique (neural nets) and an explicit approach (CBR). A series of case studies indicated that superior returns can be obtained by coupling learning systems with active trading strategies. The buy-hold strategy is the investment policy, which corresponds to the random walk model of financial markets. However, the active trading strategies supported by data mining tools outperformed the buy-hold policy, at times by a wide margin. This was true even when a moderate transaction cost was incorporated into the trades. In addition, an active strategy involving short positions could produce positive returns even in a bear market. One expected result was the synergism of multiple markets: an active strategy involving two or more markets can outperform the same strategy in any single market. An unexpected outcome, however was the hefty margin by which a multimarket portfolio can outperform a collection of isolated markets.