This script was created by training 20 selected macroeconomic data to construct artificial neural networks on the S&P 500 index .
No data were used.
The average error rate is 0.01.
In this respect, there is a strong relationship between the index and macroeconomic data.
Although it affects the whole world,I personally recommend using it under the following conditions: S&P 500 and related ETFs in 1W time-frame (TF = 1W SPX500USD , SP1! , SPY , SPX etc. )
Effective Federal Funds Rate ( FEDFUNDS )
Initial Claims ( ICSA )
Civilian Unemployment Rate ( UNRATE )
10 Year Treasury Constant Maturity Rate ( DGS10 )
Gross Domestic Product , 1 Decimal (GDP)
Trade Weighted US Dollar Index : Major Currencies ( DTWEXM )
Consumer Price Index For All Urban Consumers (CPIAUCSL)
2 - Year Treasury Constant Maturity Rate ( DGS2 )
30 Year Treasury Constant Maturity Rate (DGS30)
Industrial Production Index ( INDPRO )
5-Year Treasury Constant Maturity Rate ( : DGS5 )
Light Weight Vehicle Sales: Autos and Light Trucks (ALTSALES)
Civilian Employment Population Ratio (EMRATIO)
Capacity Utilization (TOTAL INDUSTRY) (TCU)
Average (Mean) Duration Of Unemployment (UEMPMEAN)
Manufacturing Employment Index (MAN_EMPL)
Manufacturers' New Orders ( NEWORDER )
ISM Manufacturing Index (MAN : PMI)
Artificial Neural Network (ANN) Training Details :
Learning cycles: 16231
AutoSave cycles: 100
Input columns: 19
Output columns: 1
Excluded columns: 0
Training example rows: 998
Validating example rows: 0
Querying example rows: 0
Excluded example rows: 0
Duplicated example rows: 0
Input nodes connected: 19
Hidden layer 1 nodes: 2
Hidden layer 2 nodes: 0
Hidden layer 3 nodes: 0
Output nodes: 1
Learning rate: 0.1000
Momentum: 0.8000 (Optimized)
Target error: 0.0100
Training error: 0.010000
NOTE : Alerts added . The red histogram represents the bear market and the green histogram represents the bull market.
Bars subject to region changes are shown as background colors. (Teal = Bull , Maroon = Bear Market )
I hope it will be useful in your studies and analysis, regards.
It may benefit Hang Seng, but indirectly.
While S&P is rising, all exchanges are major.
But it will fail in country-based problems.
I have previously tried to train Hang Seng with the ANN method, but I have removed the error rate is too high.
In my spare time, I will try again with other methods.