I've go dataset with more than 10 features - football skills describing players. There is also price value in each row. I would like to predict price by specifying features (skills). Initially I used linear regression, but it looks like it's not a good choice because:

  • price is high if only three skills are high (pace, goalkeeper, passing) for goalkeeper
  • price is high if defender, pace, playmaker and technique are high for defender
  • price is high if striker, technique and pace are high together for striker

etc... so it's not just linear dependency because not all skills should be considered for goalkeepers, defenders etc. Specific combination of skills makes the price high. I don't know how to tackle this and predict price by providing skills (all 10+). Do you maybe have ideas? Thanks!


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.