Performed Synthetic Minority Oversampling Technique (SMOTE) to overcome the problem of imbalance class in the customer dataset by synthesizing new examples from the existing examples. Built a XGBoost model and achieved over 93% AUC score in predicting churn of the customer. Found out the most important feature that impacted customer churn was the total transaction count for the past 12 months. AutoEDA of the Customer Dataset using Pandas Profiling Link to Google Colaboratory Notebook with Explanation

Utilized BeautifulSoup library to scrape Indeed job offerings data based on job title and job location specified. Stored the output in a CSV file for easier comparing between different offerings in a single file without the need of opening many tabs or going back of forth in a tab. This helped us to filter out irrelevant offerings to us before proceeding to view for further information in the Indeed website and applying for the jobs.

Performed word preprocessing such as noisy text and stopwords removal. Conducted feature transformation to convert text data into numerical features using Tokenizer before converting the generated tokens into sequences and applying padding so that each input sequence became in the same length. Used Sequential API in Keras including the Embedding and LSTM Layer. Utilized GloVe Embeddings to build the embedding matrix for the Embedding Layer. Achieved nearly 1.00 in F1 score in classifying real or fake news.