The goal is to use Lasso Regression to build a model between the IMDb ratings of each episode with their casts, writer, and producers. We will also tune the penalty parameters and sort out the feature importance.

Implementing Principle Components Analysis on the best Hip-Hop Songs from BBC poll of music critics. Extract features from Spotify API, then clean and engineer it. Finally, check out what are the common features of these great tracks.

On-going projects

on going program

Web-scrapping data with Python; EDA with R; Modeling with R;

Vending machines, based on the concept of online operation, provide convenient offline services, save labor costs with small, self-service operation mode, and make affordable, high-quality goods within reach, becoming another mainstream mode of current retail operation. The supply frequency, type selection, supply quantity, and station selection of the products in the vending machine are the problems that the vending machine operators need to focus on. Therefore, scientific business data analysis can help operators to understand user needs, grasp the demand for commodities, and provide users with accurate and intimate services. It is an essential means to grasp the business direction, and it is of considerable significance to the development of the vending machine marketing model. Five vending machines, numbered A, B, C, D, and E, were installed in different locations in A mall. The commodity sales data of each vending machine from January 1, 2017, to December 3, 2017, are provided.

Introduction The US Adult Census dataset is a repository of 48,842 entries extracted from the 1994 US Census database. This report first starts exploratory analysis on the original dataset with great visualizations and illustrations. Then, machine learning algorithms are applied to classify the income level of people. The AUC for our model is up to 0.9755!

My first publish on RPubs.