fumanguyen Goto Github PK

blight-violation-prediction

Using Machine Learning to Predict whether a blight violation ticket in Detroit city would be compliant or non-compliant

bobblehead-mlb

Applying multi-level model on panel data to evaluate the performance of bobbleheads promotion

drivetime-sedans-used-vehicle-market

Linear regression model applied in the used vehicle market to guide the inventory selection process

eda-python-b2b-marketing

goodyear_tire_demand-production

In this project, we use time series data to forecast Tire Replacement Demand of Passenger Vehicle segment based on Vehicle Miles Travel (VMT) and Producer Price Index for Tire (PPI-Tire)

hands-on-data-analysis-with-pandas-2nd-edition

Materials for following along with Hands-On Data Analysis with Pandas – Second Edition

loans

Testing github

machine-learning-advertising

Using machine learning on advertising data to optimize its performance

meetup

SQL for Meetup API data

model--building--hr

The Ultimate Precision Instrumentation Company produces highly technical industrial instrumentation devices. The human resources (HR) director has the business objective of improving recruiting decisions concerning sales managers. The company has 45 sales regions, each headed by a sales manager. Many of the sales managers have degrees in electrical engineering, and due to the technical nature of the product line, several company officials believe that only applicants with degrees in electrical engineering should be considered. At the time of their application, candidates are asked to take the Strong-Campbell Interest Inventory Test and the Wonderlic Personnel Test. Due to the time and money involved with the testing, some discussion has taken place about dropping one or both of the tests. To start, the HR director gathered information on each of the 45 current sales managers, including years of selling experience, electrical engineering background, and the scores from both the Wonderlic and Strong-Campbell tests. The HR director has decided to use regression modeling using a 10% significance level to predict a dependent variable of “sales index” score, which is the ratio of the regions’ actual sales divided by the target sales. The target values are constructed each year by upper management, in consultation with the sales managers, and are based on past performance and market potential within each region. The Minitab file Question 6 contains information on the 45 current sales managers. The following variables are included: Sales—Ratio of yearly sales divided by the target sales value for that region; the target values were mutually agreed-upon “realistic expectations” Wonder—Score from the Wonderlic Personnel Test; the higher the score, the higher the applicant’s perceived ability to manage SC—Score on the Strong-Campbell Interest Inventory Test; the higher the score, the higher the applicant’s perceived interest in sales Experience—Number of years of selling experience prior to becoming a sales manager Engineer—Indicator variable that equals 1 if the sales manager has a degree in electrical engineering and 0 otherwise

nlp-with-python

Scikit-Learn, NLTK, Spacy, Gensim, Textblob and more

text-mining-sentiment-tripadvisor

Analyze hotel review data on TripAdvisor