In this project, I use a telecom dataset to predict whether a customer will churn based on their usage, service complaints, and other features. This involves handling imbalanced data and feature engineering.
Metric to optimize: Accuracy and F1-score.
Dataset: Link
The goal is to predict churn in the best possible manner. The column names in the dataset should be self-explanatory.
This project involves using sensor data from machines to predict when maintenance should be performed to prevent unexpected failures. This will involve time-series analysis and possibly dealing with large, noisy datasets.
Metric to optimize: RMSE.
Dataset: Link
The goal is to predict the remaining useful life (RUL) of each engine in the test dataset based on the entire life cycle data. RUL is equivalent to the number of flights remaining for the engine after the last datapoint in the test dataset.
Twitter has emerged as a vital platform for communication during emergencies. The widespread use of smartphones allows individuals to report emergencies as they happen in real time. Consequently, an increasing number of organizations, including disaster relief agencies and news outlets, are showing interest in systematically tracking Twitter. However, determining whether someone's posts genuinely indicate a disaster can often be challenging.
Metric to optimize: F1-Score, Accuracy
Dataset: Link