Python

In this project, a Recurrent Neural Network (RNN) model was developed to classify tweets as complaints or non-complaints directed towards airlines. The project involved several steps, starting with data acquisition, where tweets were downloaded and extracted. Preprocessing steps included cleaning the text by removing URLs, converting mentions and hashtags, eliminating numbers and punctuation, and applying lemmatization. The data was then tokenized and sequenced for model input.

The project conducted by Team Robolytics provides a thorough analysis of the booking data of Global Hotels and Resorts (GHR) to enhance revenue management strategies. By employing tools such as Python, R, and Tableau, the team has identified key revenue streams from hotel stays, losses from room upgrades and cancellations, and developed predictive models to forecast potential revenue losses. The analysis also delves into the effectiveness of booking channels and market segments. To optimize revenue, the team recommends implementing tiered cancellation fees, regulating upgrades, promoting loyalty programs for corporate customers, and crafting specialized packages for deluxe rooms. These strategic suggestions are aimed at boosting GHR’s revenue, which has the potential to reach over $19 million.

In this project, we dive into the subjective world of human attractiveness, using the power of deep learning to tackle a question as old as time: "Am I hot or not?" Leveraging a dataset of over 200,000 celebrity faces from the CelebFaces Attributes Dataset (CelebA), each annotated with binary attributes including "Attractive," our model—dubbed BeautyAI—aims to predict the allure of a face.

AI application that takes an image and creates a musical composition from it.