1

I am working with health dataset.

The dataset is about body signals (8 features) and the target variable is body failing Temperature. There were 6 different temperatures or Multi classes. (targets)

My data set is of shape (1500*9) - Numerical Data

I fitted my data with RMClassifier, but it shows a accuracy of around 80% But i needed my accuracy & F1 score to be improved even more. On the other hand I am tweaking some parameters for better accuracy.

Apart from Random Forest, I would like to get some suggestion, which model would be the best choice fr my above problem. Since my dataset is small, I am not sure about selecting the best ML model

I thought of going with boosting,SVM or Neural Nets. Kindly share your thoughts.

Mari
  • 698
  • 1
  • 8
  • 27
  • 1
    This question is off topic for stack overflow, as it relates more to theory or technique than to actual coding. It might be a better question for the [stats.se] or [datascience.se] stack sites – G. Anderson Feb 14 '20 at 16:20

1 Answers1

2

To find the best model for your problem you can use GridSearchCV of Scikit-learn. Use pipeline and configure the GridSearchCV to experiment with different learning methods changing their hyper-parameters. It will find the best ML model for you.

A group of researchers found with quality and quantity data the performance of different ML models vary a little (Hands-On Machine Learning with Scikit-Learn and TensorFlow, first edition, page 23). You should also spend some effort on feature engineering to see if you can increase the number of features. You can get some idea from this Titanic solution

Ashiqur Rahman
  • 71
  • 1
  • 7