Product Quantization using Regression

Abstract

Approximate Nearest Neighbor (ANN) has developed an immense demand for many tasks. This ANN methodology was being used for product quantization. These product quantization methods were being used for e-commerce sites. However, this quantization maybe sometimes misleading due to a lack of accuracy in technique. So, we managed to increase the accuracy of quantization by adding Logistic Regression in the process. This helps to increase the accuracy of the method by having a probability value. This helps to make correlated items much more accurate when compared to pure quantization. This method is helpful for e-commerce sites for efficiency in the prediction of purchase by the customer.