In this Challenge, you’ll assume the role of a financial advisor at one of the top five financial advisory firms in the world. Your firm constantly competes with the other major firms to manage and automatically trade assets in a highly dynamic environment. In recent years, your firm has heavily profited by using computer algorithms that can buy and sell faster than human traders.
The speed of these transactions gave your firm a competitive advantage early on. But, people still need to specifically program these systems, which limits their ability to adapt to new data. You’re thus planning to improve the existing algorithmic trading systems and maintain the firm’s competitive advantage in the market. To do so, you’ll enhance the existing trading signals with machine learning algorithms that can adapt to new data.
After running the SVM Model and comparing the results. The SVM plot performed worse than the actual results. When looking at the training report the precision for -1.0 was 0.56 and for 1.0 was 0.58. After plotting the results you can see where the strategy returns for SVM get worse.
After running the Logistical Regression Model and plotting the data the Logistical Regression Model did much better than the actual returns did. The logistical regression was able to perform better then both the SVM model and the actual returns from the dataframe. The precision score for -1.0 was 0.53 and for 1.0 it recieved 0.52. I have provided both of my plots below so the results can be observed.
