Rodolfo Maciéczyk

Tableau Dashboard to explore the churn effect by the average annual temperature in a fictitious company.

BI analysis done with Tableau Desktop Professional.

NLP application using a BERT transformer model.

Done using JavaFx, the purpose of the application is to assist a global consulting organization in managing the appointments of their customers with the firm's contacts. The application allows to add, edit and delete customers and appointments, and has different kind of alerts that prevent errors such as scheduling an appointment in a weekend. Click above for more information and a video demo.

This was a project regarding an interesting dataset of cancelled flights. My end goal was to create a step-by-step guide to process, train, execute and evaluate the dataset combining Spark and Google Colab.

Using a dataset from China’s largest third-party mobile data platform, TalkingData, the objective was to predict user’s demographics characteristics which in return gives us valuable information that can help millions of developers and brand advertisers pursue data-driven marketing efforts which are relevant totheir users and catered to their preferences.

Training and testing data from 7042 customers from a Telco with eight different supervised models, the code predicted customer churn with a 78 % accuracy. It also determined the most important features that influence churn.

The goal of this project is to train a model with texts from different authors,and determine the accuracy of the model when predicting from which author a new text belongs.