ML-Based Interconnected Affecting Factors with Supporting Matrices for Assessment of Risk in Stock Market

Algorithm 1

Price fluctuate method.

Input : company stocks , PredictedY

for i in company_stocks(0,1) do

Train data and Daily profit is computed in the column profit.

Order = [1 if signal > 0 else -1 for signal in Train['PredictedY']]

Place buy order for signal 1 else sell order for -1

Profit = Train['company_stock'] Train['Order']

Wealth = Train['Profit'].cumsum()

Test data and Proft of price fluctation method

Order = [1 if sig >0 else -1 for sig in Test['PredictedY']]

Place buy order for sig 1 else sell order for -1

Profit = Test['company_stock'] Test['Order']

Wealth = Test['Profit'].cumsum()

End for

Function performance()

For i in index[0]

do

Include The initial investment which is one price of company_stock.

Compute Sharpe Ratio on Train data and Test data

Output : Daily (dailyr.mean()/dailyr.std(ddof=1))

Evaluate Maximum Drawdown in Train data and Maximum Drawdown in Test data

Output : (['Drawdown'].max())

End for

Return Output

End function