Original Summary

I have more or less working more or less market making algorithm (eat the spread).<p>It works extremely well at 1 lot trades, but once you increase the volume profits reach maximum at some point once you do significant turnover compared to the rest. It&#x27;s kinda obvious, you got adverse selected more and more.<p>What bothers me - maybe I simply quote inefficiently? I tried a lot of of approaches (imbalance, skewing, VWAP, hand crafted signals), and at some point they stopped improving my PnL.<p>Any way to estimate theoretical capability of the specific market? Is this market already exhausted and you just can&#x27;t do anything else here.<p>Assuming that market indeed can be exhausted, it&#x27;s not some US bonds&#x2F;top stocks with infinite volumes.<p>And side question about backtesting. Is it even worth it? Now I filter past trades with new signals. Predictions of new trades suck for me, in real life competitors instantly react on my orders, so backtest overestimates PnL.

  • 情报分类：商业与市场研究
  • 分类依据：内容涉及商业、投资或市场动态
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/26 07:29:43