-
Notifications
You must be signed in to change notification settings - Fork 3.7k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Backtesting result calculation is weird #203
Comments
Hey @h4l-yup - which agent(s) and LLM did you use? |
I am running into the same issue with the AI signal "flip-flopping." I was wondering if there is a way to make decisions more deterministic and implement a delta to buffer the flip-flopping and reinforce conviction. |
@virattt But when I used Cathie Wood agent, it seems it has similar issues. |
Same issue here. I used Technical Analyst, Fundamentals Analyst, Sentiment Analyst and Valuation Analyst together with the deepseekR1 model. This is the command that I used : And this is the result : +------------+----------+----------+------------+---------+----------+------------------+-----------+-----------+-----------+ PORTFOLIO PERFORMANCE SUMMARY: Sharpe Ratio: 15.13 |
The value of the cash balance increases on short positions but other summay values are OK
I just made a pull request that could fix the issue. Could you please review it ? Thank you |
Describe the bug
poetry run python src/backtester.py --ticker TSLA --start-date 2024-12-01 --end-date 2024-12-20
This was my command and below is the result.
As you can see, the price of Tesla just goes up and the ai made all the decisions of SHORT.
Therefore it can not make profits at all but the result says total value goes up.
The text was updated successfully, but these errors were encountered: