Year of Graduation
Building a Price Prediction Model Using Machine Learning Techniques
Big Data Systems
This thesis compares machine learning methods to test which one performs the best in predicting a price in the community-powered marketplace according to features such as user-inputted text descriptions of their products, including details like product category name, brand name, and item condition. The dataset was chosen from one of the biggest e-commerce company's selling shopping platform. Experimental results show that recurrent neural network in combination with an intensive data preprocessing outperforms in price prediction based on item text description.