microsoft / microsoft/qlib

High rmse with excellent AR

Open
#1,696 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Python
Stars
48.7k
Forks
7.7k
PR merge metrics
No merged PRs in 30d

Description

❓ Model biases with XGBoost

I have been tuning my XGBoost hyperparameters. I have very poor rmse' on both train and validation but excellent backtesting results. Essentially those also convert well into paper trades on long positions.

I have imputed some portions of my data to cover missing volume numbers in certain years. This although has been done using interpolation as a series.

I'm trying to figure out anty biases the model might have(or rather I might have) with such a situation. Thoughts appreciated.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or reproducible configuration are named. Start by comparing the training and validation RMSE setup with the backtesting and paper-trading setup, then examine how interpolated missing volume data enters each path. Done would require a reproducible diagnosis of the discrepancy and a clearly scoped correction.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
data, machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.