Forecasting directional movement of Forex data using LSTM with technical and macroeconomic indicators

Financial Innovation

Table 17 Hybrid model (on extended dataset): one-day-ahead predictions

Iterations		Hybrid model-modification based on ME_LSTM		Hybrid model-modification based on TI_LSTM
ME_LSTM	TI_LSTM	Profit_accuracy (%)	# of transactions	Profit_accuracy (%)	# of transactions
50	50	55.42	83/152	53.01	83/152
50	100	59.38	96/152	61.46	96/152
50	150	74.63	67/152	76.12	67/152
50	200	81.82	52/152	81.82	52/152
100	50	64.18	67/152	67.16	67/152
100	100	59.49	79/152	65.82	79/152
100	150	66.04	53/152	73.58	53/152
100	200	75.34	84/152	74.65	84/152
150	50	60.47	86/152	55.81	86/152
150	100	57.73	97/152	61.86	97/152
150	150	69.12	68/152	75.00	68/152
150	200	84.13	75/152	84.38	75/152
200	50	83.08	71/152	81.36	71/152
200	100	79.31	67/152	79.66	67/152
200	150	79.31	64/152	78.18	64/152
200	200	85.45	62/152	85.19	62/152
Average		70.93	73.19/152	72.19	73.19/152