Wish_Products_Rating_Prediction

Introduction

This dataset comes from wish.com and this is an American online E-commerce platform for transactions between sellers and buyers.

We have some features collected by their rating and based on this information we need to predict the rating of a new product.

Problem Formulation

Define the problem. What is the input? What is the output?

The problem is to predict the product ratings of Wish.com products based on other features of the products. The input is the various features of the products such as product type, description, price, and image, among others. The output is the predicted product rating, which is in categories from 1 to 5. The goal is to estimate how likely people will like a product and understand the conditions under which a product will be highly rated.

What data mining function is required?

The data mining function required is classification since the goal is to predict the product rating which is discrete, based on other features of the product.

What could be the challenges?

The challenges could include dealing with noisy data, missing values, and irrelevant or unnecessary features. Also, the features included in the dataset may not be sufficient to accurately predict the product rating, which may require additional data sources or feature engineering.

What is the impact?

The impact of accurately predicting the product rating is that it can help businesses understand their customer base and tailor their products to meet customer preferences. It can also help businesses identify the features that are most important to customers, which can inform product development and marketing strategies.

What is an ideal solution?

For Me Decision Tree Was the best model for this problem. but in general, An ideal solution would be to develop a machine learning model that accurately predicts the product rating based on the available features, while also being able to handle missing or noisy data. The model should also be easily interpretable, so that businesses can understand the factors that are most important for predicting product ratings. Additionally, the model should be regularly updated with new data to ensure its accuracy over time.