PROJECT PRESENTATION

    Data Science Club at UTD is extremely excited to present our next event for the Spring 2019 semester: Project Presentation! During this event, teams out of a total of 60 students who are mentored by David Hagar, Head R&D Hypergiant Sensory Sciences, are going to present their data science projects. There will be a feedback session, during which the panel comprising of industry professionals and professors will provide their valuable opinions and insights on the projects.

    This is not only a good chance to see how the team’s approach and solve real-world data science problems, but it is also a good opportunity to network with experts from the industry and seek guidance from experienced students. There will also be fun and educational games awaiting!

Upon successful registration, you can catch up on the following projects.

 

Event Details:

Date: 25th February, 2019

Time: 4:00 PM to 7:00PM

Venue: Davidson Auditorium (JSOM 1.118)

Please Register Here:

https://www.dsc-utdallas.org/events-1/dsc-project-presentation  (Click)               

We are looking forward to seeing you!

Project Abstract:

VA Maverick: Recommending Fashion Trends

  The Global fashion industry is valued at 3 Trillion Dollars and accounts for 2 % of World's GDP. The Fashion industry is undergoing a dramatic transformation by adopting new computer vision, machine learning and deep learning techniques. In this project, we are a virtual stylist assistant hired by an online retailer that looks at customer images and classify what fashion category they are wearing like bags, dresses and pants. The virtual assistant can help retailer detect and forecast fashion trends and launch targeted marketing campaign.

Prediction of Nephrotic Syndrome using Clinical Report

Nephrotic syndrome involves the loss of a lot of protein through urine. A kidney biopsy is often required to diagnose the underlying pathology in patients with suspected glomerular disease. The goal of the project is to build a clinical support system that predicts the disease using clinical features, thus reducing the need of kidney biopsy.

Smart Expenditure Tracker

So, have you ever wondered where all your money is going?  “Be like, I know I’m spending $25 at Walmart, but what am I spending it on?“… Look No more. The project Receipt Tracker is an attempt at efficiently managing the receipt expenses. It extracts information such as vendor, time and date of purchase, purchased items, total spendings, etc. from the receipt and creates a category-wise expenditure trend. This enables the end user, mainly me, to get a better insight into how “bad” their spending habit is.

Superbowl Analytics, Apollo Voice Assistant, Movie Recommendation Engine

Superbowl Analytics

- Adding to the buzz and the hype around Superbowl, let’s have a peak into Superbowl using BI integration with Cloud services such as Redshift and S3.

Apollo Voice Assistant

- A voice assistant project which involves Speech recognition, NLP, machine learning, parallel processing fundamentals and Python.

Movie Recommendation Engine

- A Movie Recommendation System which has been developed with a front end using machine learning in python with front end in Django. 

Predicting Soccer Match Results to Improve Chances of Winning Bets

Soccer is one of the most renowned and most played games all around the world. It’s a gambler’s paradise; the one who makes the right decisions gets flooded with money. Being soccer lovers, we decided why not assist such people with some insights and predictions on winners using the knowledge of machine learning and the game we love. So we have decided to create a model that predicts the results of soccer matches in order to assist the decision-making process and maximize returns in the betting world.

Facial Recognition using FaceNet

Build an end-to-end facial recognition project using google Facenet, Google colab and GCP/AWS to provide a simple security entry control. Also, plan to give an opportunity for attendances to upload their face photos to experience our model.

Smart Expenditure Tracker

So, have you ever wondered where all your money is going?  “Be like, I know I’m spending $25 at Walmart, but what am I spending it on?“… Look No more. The project Receipt Tracker is an attempt at efficiently managing the receipt expenses. It extracts information such as vendor, time and date of purchase, purchased items, total spendings, etc. from the receipt and creates a category-wise expenditure trend. This enables the end user, mainly me, to get a better insight into how “bad” their spending habit is.

Credit Card Fraud Detection

It is important that credit card companies are able to recognize fraudulent credit card transactions so that customers are not charged for items that they did not purchase. A data set containing nearly 0.3M credit card transactions, with a very high imbalance (Only 0.17% fraudulent transactions) is used to create a robust Machine Learning model that can be used to identify fraudulent transactions with high accuracy and minimum False Positive rate.

©2020 by Data Science Club