31. Explain the process of data overfitting. How to resolve it?

Overfitting takes place when a statistical model or machine learning algorithm captures the noise of the data. This causes an algorithm for showing the low bias but high variance in the outcome. However, it can be prevented using:

• Firstly, Cross-validation. This helps in splitting the training data in order to create multiple mini train-test splits. Which further, can be used for tuning model.
• Secondly, training data. Providing more data to the machine learning model can help in good analysis and classification. 
• Thirdly, removing features. There are sometimes irrelevant features that are not required for analysis. They can result in increasing the complexity of the model, thus leading to possibilities of data overfitting. 
• Next, Early stopping. A machine learning model is trained iteratively, this provided access to examine how well each iteration of the model performs. Frequent iterations can lead to overfitting.
• Lastly, using Ensemble models. This refers to a technique used for creating multiple Machine Learning models, which are then combined to make more accurate results.