Portfolio Trader最佳化的Robustness

abula

如題，使用圖表時最佳化可以設定Robustness決定穿透IS跟OSS的參數
不知道在portfolio trader中是否也能這樣設定?

abula

自己來回應，程式碼如下。這個程式是用官方!optimiza by sharpe ratio改的，主要邏輯是用array定義我預設的四個樣本週期，進行迴圈以計算樣本內外的netprofit，最後計算各個IS與OOS的年化報酬率來計算WFE。未通過的給一個很大的負值(-9999)。

好處是可以用WFE當作濾網來過濾樣本外表現差的參數，壞處是自己需要手動輸入Inputs(我現在做法是先跑很少參數的WFO看日期，然後手動輸入)。我一開始有想要讓程式自己算例如 currentdate-X days的方式，但台指期交易日不能完全對的上，如果你像我一樣跑的期間都至少六七年，那四個去跑十年資料應該夠，也不會太麻煩。

1. 
   
2. Inputs:
   
3.   InitialCapital(10000),  // Initial capital
   
4.   AnnualRiskFreeRate(0.02), // Annual risk-free interest rate
   
5.   Period(0), // 0=monthly, 1=daily
   
6.   IS_StartDate1(0), IS_EndDate1(0), OOS_StartDate1(0), OOS_EndDate1(0),
   
7.   IS_StartDate2(0), IS_EndDate2(0), OOS_StartDate2(0), OOS_EndDate2(0),
   
8.   IS_StartDate3(0), IS_EndDate3(0), OOS_StartDate3(0), OOS_EndDate3(0),
   
9.   IS_StartDate4(0), IS_EndDate4(0), OOS_StartDate4(0), OOS_EndDate4(0);
   
10. 
    
11. Arrays:
    
12.   IS_StartDates[4](0), // Array to store start dates of In-Sample periods
    
13.   IS_EndDates[4](0), // Array to store end dates of In-Sample periods
    
14.   OOS_StartDates[4](0), // Array to store start dates of Out-of-Sample periods
    
15.   OOS_EndDates[4](0); // Array to store end dates of Out-of-Sample periods
    
16. 
    
17. Vars:
    
18.   PeriodIndex(0),
    
19.   IS_Profit(0),
    
20.   OOS_Profit(0),
    
21.   IS_AnnualReturn(0),
    
22.   OOS_AnnualReturn(0),
    
23.   IS_CurrentProfit(0),
    
24.   OOS_CurrentProfit(0),
    
25.   SharpeValue(0),
    
26.   FitnessValue(0),
    
27.   PrevISNetProfit(0), // Previous net profit at the start of the In-Sample period
    
28.   PrevOOSNetProfit(0); // Previous net profit at the start of the Out-of-Sample period
    
29. 
    
30. // Initialize arrays only on the first bar of data
    
31. If CurrentBar = 1 Then Begin
    
32.   IS_StartDates[1] = IS_StartDate1; IS_EndDates[1] = IS_EndDate1; OOS_StartDates[1] = OOS_StartDate1; OOS_EndDates[1] = OOS_EndDate1;
    
33.   IS_StartDates[2] = IS_StartDate2; IS_EndDates[2] = IS_EndDate2; OOS_StartDates[2] = OOS_StartDate2; OOS_EndDates[2] = OOS_EndDate2;
    
34.   IS_StartDates[3] = IS_StartDate3; IS_EndDates[3] = IS_EndDate3; OOS_StartDates[3] = OOS_StartDate3; OOS_EndDates[3] = OOS_EndDate3;
    
35.   IS_StartDates[4] = IS_StartDate4; IS_EndDates[4] = IS_EndDate4; OOS_StartDates[4] = OOS_StartDate4; OOS_EndDates[4] = OOS_EndDate4;
    
36. End;
    
37. 
    
38. // Calculation and strategy logic
    
39. For PeriodIndex = 1 to 4 Begin
    
40.   // Check if PeriodIndex is within the bounds of the arrays
    
41.   If (PeriodIndex >= 1) and (PeriodIndex <= 4) Then Begin
    
42. 
    
43.     // Existing logic for In-Sample and Out-of-Sample Periods
    
44.     // ...
    
45. 
    
46.   End; // End of bounds check
    
47. End;
    
48. 
    
49. For PeriodIndex = 1 to 4 Begin
    
50.   // In-Sample Period Logic
    
51.   // Check if the current date is within the In-Sample period
    
52.   If Date >= IS_StartDates[PeriodIndex] and Date <= IS_EndDates[PeriodIndex] Then Begin
    
53.     // On the start date, store the current net profit as the previous In-Sample net profit
    
54.     If Date = IS_StartDates[PeriodIndex] Then PrevISNetProfit = NetProfit;
    
55.     // On the end date, calculate the profit for the In-Sample period
    
56.     If Date = IS_EndDates[PeriodIndex] Then Begin
    
57.       IS_CurrentProfit = NetProfit - PrevISNetProfit;
    
58.       IS_Profit = IS_Profit + IS_CurrentProfit;
    
59.       // Calculate annualized return for the In-Sample period
    
60.       IS_AnnualReturn = (IS_CurrentProfit / InitialCapital) / (IS_EndDates[PeriodIndex] - IS_StartDates[PeriodIndex] + 1) * 365;
    
61.     End;
    
62.   End;
    
63. 
    
64.   // Out-of-Sample Period Logic
    
65.   // Check if the current date is within the Out-of-Sample period
    
66.   If Date >= OOS_StartDates[PeriodIndex] and Date <= OOS_EndDates[PeriodIndex] Then Begin
    
67.     // On the start date, store the current net profit as the previous Out-of-Sample net profit
    
68.     If Date = OOS_StartDates[PeriodIndex] Then PrevOOSNetProfit = NetProfit;
    
69.     // On the end date, calculate the profit for the Out-of-Sample period
    
70.     If Date = OOS_EndDates[PeriodIndex] Then Begin
    
71.       OOS_CurrentProfit = NetProfit - PrevOOSNetProfit;
    
72.       OOS_Profit = OOS_Profit + OOS_CurrentProfit;
    
73.       // Calculate annualized return for the Out-of-Sample period
    
74.       OOS_AnnualReturn = (OOS_CurrentProfit / InitialCapital) / (OOS_EndDates[PeriodIndex] - OOS_StartDates[PeriodIndex] + 1) * 365;
    
75.     End;
    
76.   End;
    
77. End;
    
78. 
    
79. // Calculate the Sharpe Ratio and custom fitness value on the last bar of the chart
    
80. if LastBarOnChart_s then begin
    
81.   // Calculate the Sharpe Ratio using the built-in function
    
82.   SharpeValue = SharpeRatio(Period, AnnualRiskFreeRate, LastBarOnChart_s, InitialCapital);
    
83. 
    
84.   // Check if the Out-of-Sample annualized return is greater than 50% of the In-Sample annualized return
    
85.   If OOS_AnnualReturn > 0.5 * IS_AnnualReturn then begin
    
86.     FitnessValue = SharpeValue; // If true, set the fitness value to the Sharpe Ratio
    
87.   end else begin
    
88.     FitnessValue = -9999 + SharpeValue; // If false, penalize the fitness value
    
89.   end;
    
90.   
    
91.   // Set the custom fitness value for the strategy
    
92.   SetCustomFitnessValue(FitnessValue);
    
93. end;
    
94. 
    

複製代碼

rc76

PT的WFA好像沒有MC的WFA多功能?

請問這個code是放在PT的MM信號內還是?