Data imputation and comparison of custom ensemble models with existing libraries like XGBoost, Scikit learn, etc. for Predictive Equipment failure

TL;DR

This paper compares custom ensemble models with existing libraries like XGBoost and Scikit-learn for predicting equipment failure, focusing on data imputation strategies for datasets with missing values in oil extraction equipment.

Contribution

It introduces novel data imputation strategies and details the architecture and training process of custom ensemble models for predictive maintenance.

Findings

Custom ensemble models outperform existing libraries in accuracy.

Effective data imputation improves model performance.

Detailed methodology aids reproducibility.

Abstract

This paper presents comparison of custom ensemble models with the models trained using existing libraries Like Xgboost, Scikit Learn, etc. in case of predictive equipment failure for the case of oil extracting equipment setup. The dataset that is used contains many missing values and the paper proposes different model-based data imputation strategies to impute the missing values. The architecture and the training and testing process of the custom ensemble models are explained in detail.