"10 Ways Backtests Lie" by Tucker Balch

แชร์
ฝัง
  • เผยแพร่เมื่อ 5 ม.ค. 2025

ความคิดเห็น • 10

  • @nustaimo6755
    @nustaimo6755 4 ปีที่แล้ว +9

    He joined J.P. Morgan AI Research as Managing Director in Jan 2019

  • @jdgcreative
    @jdgcreative 10 หลายเดือนก่อน

    who else is here after their backtest returns 7.377e+21% apr

  • @arfa9601
    @arfa9601 4 ปีที่แล้ว +5

    “Don’t forward test”

  • @t_ionk5688
    @t_ionk5688 3 ปีที่แล้ว +1

    can anyone please tell me what the last gentleman to ask a question, was talking about.Thank you.

    • @Hello-cjqofb169
      @Hello-cjqofb169 25 วันที่ผ่านมา

      some people use other ways to make their backtest more robust, like bootstrapping
      trades and (Inaudible). Do you use this technique in practice?

    • @Hello-cjqofb169
      @Hello-cjqofb169 25 วันที่ผ่านมา

      The bootstrap method works by repeatedly computing a metric on random samples drawn from the backtest’s returns. Then, the metric is computed on each random sample, and the average is taken. By doing this on thousands of random samples, we obtain a more robust and accurate estimate of the metric. So this is to see that whether our amazing backtesting result is just obtained by luck. In Monte Carlo simulation, if we simulate equity paths, being lucky means we get the equity curve with the highest return at the end. However, in real trading, the probability of picking this lucky equity curve is very low.

  • @jonesr227
    @jonesr227 7 ปีที่แล้ว +5

    His book is $35 for 148 pages on Amazon. So, counter to claims to the contrary, it's not cheap.

    • @StephenRoseDuo
      @StephenRoseDuo 7 ปีที่แล้ว +4

      jonesr227 a book should be judged by its content not its pages

    • @Zambito1
      @Zambito1 7 ปีที่แล้ว +8

      He says it's $5 in the video though.

  • @Pietrabentivi
    @Pietrabentivi 4 ปีที่แล้ว

    Nice