Description:
In this project, I predicted the price of products based on the descriptions provided by sellers. All descriptions were in Persian and included details about the product, such as category, brand name, etc.
Process:
- Data preprocessing
- Removing punctuations and non-alphabetic characters
- Replacing Arabic letters with Persian ones
- Removing stop words
- Feature extraction using the bag of words and TF-IDF vectorizers and One-hot encoding
- Feature selection using Pearson's correlation coefficient
- Price prediction using random forest and linear regression
Code:
