Negative reviews summarization
2This project aims to summarize all negative reviews of a product and classify them in one of the topics in a few words to detect which are the main customer complaints about it. The model is deployed in AWS and stakeholders can access these words by entering the product ID in a gradio web API.
Respiratory Classification
This project predicts which type of SARS virus a patient has contracted using an XGBoost model. The model is deployed on AWS using SageMaker, and a medical form for patient data input is available via a Streamlit web API.
Laptop Price Elasticity
This project aims to determine the price elasticity of demand for laptops sold by Best Buy using simple linear regression. The goal is to establish optimal pricing strategies to maximize revenue. Data on significant products with calculated price elasticity is accessible through a Streamlit app. The app also simulates the potential increase in demand and revenue if prices are reduced by 10%.
Olist sales Power BI Report
Olist is the largest department store in Brazilian marketplaces. Olist connects small businesses from all over Brazil to channels without hassle and with a single contract. Those merchants are able to sell their products through the Olist Store and ship them directly to the customers using Olist logistics partners. They want to get more knowledge and more actionable insights about their order data. A POWER BI report with some dashboards was created to analyze this dataset.
Website A/B testing
This is an A/B testing project that was made to see if a new version of a sign up button in a website is better than current one. This A/B testing was made using a reinforcement learning algorithm called Multi-Bandit Armed (MAB) with a bayesian agent (Thompson Sampling).
High customers identification
This is an end-to-end data science project which a clusterization algorithm was used to select most valuable customers in order to create a loyalty program called insiders. Also, a dashboard in Metabase was created to monitoring these customers and their metrics. This dashboard is hosted in a EC2 service provided by AWS.
Health insurance cross-sell
This is an end-to-end data science project which a classification algorithm was used to rank clients which would be interested in getting a car insurance. It was used machine learning Random Forest algorithm to sort these clients. The deployment was done in an AWS cloud server (EC2) and results was accessed through Google sheets.
Rossman Sales Prediction
This is an end-to-end data science project which predict sales of the next six weeks of Rossmann stores. It was used machine learning XGBoost algorithm to predict these sales. APIs and model was hosted in a EC2 server of AWS cloud. Predictions of each store can be accessed by users through Telegram as shown below.
KC House Data Insights
KC House is a company that makes money getting good opportunities of buying properties and sell them. It also may make improvements in some properties bought to increase their values before selling. The issue arise in picking out such good opportunities to maximize their profit. It needs to know which houses to buy and for how much it ought to sell them.