The problem of predicting financial time-series data is an issue of a much interest to both economic and academic communities. Decisions regarding investments and trading by large companies and the economic policy of governments rely on computer modelling forecasts. The foreign currency exchange rates are very important in this respect, with FX market worth an estimated daily trading volume of 1 trillion US Dollars.
Most financial data is non-stationary by default, this means that the statistical properties of the data change over time. These changes are caused as a result of various business and economic cycles (e.g. demand for air travel is higher in the summer months, this can have a knock-on effect of exchange rates, fuel prices, etc). While this information should be taken into account in the current closing price of a stock, share or exchange rate it still means that long term study of the behaviour of a given variable is not always the best indicator of its future behaviour.
Traditional methods for time series forecasting are statistics-based, including moving average, autoregressive, autoregressive moving average models, linear regression and exponential smoothing. These approaches do not produce fully satisfactory results, due to the nonlinear behaviour of most of the natural occurring time series. Other more advanced techniques such as neural networks, fuzzy logic and fractals have been successfully used in time series prediction.
This keynote speech addresses the problem of financial time series prediction using advanced machine learning approaches.