Kernel-Based Aggregating Learning System for Online Portfolio Optimization

Figure 2

The whole two-step price relative prediction scheme of KAL. By comparing close price with its moving average in a fixed time window, indicator information is revealed. Then, peak or nadir prices of different assets are picked up. By combining them with online outputs of the ARIMA model, the future price prediction with the component estimator is produced. At last, by aggregating multiple component estimators, the final predicted value is generated.