Intraday forex bid/ask spread patterns - Analysis and forecasting

In the foreign exchange, market liquidity is represented by the best bid and the best ask price spread. We searched for liquidity patterns during 24h trading sessions After experimental comparison, we found that neural networks and regression trees are most suitable for liquidity forecasting and outperform simple averaging and regression. We also rated the factors that most influence forecasting accuracy. Time of day is the factor that influences liquidity the most, followed by day of the week. Month and day of the month have no effect on liquidity. As a final conclusion, we state that in most currency pairs the liquidity can be forecasted more accurately than the simple averaging which is often used in practice for planning large order execution.