PROJECTS

Project Image
Lyrics Machine

Generates lyrics by n-grams and markov chains

GithubWebsite
Project Image
Talk Like Ted

In this project, we carried out Statistical Analysis and Text Analysis on TED Talk data. In Statistical Analysis, we explored the relationships among the attributes and built a regression model to predict the viewership and comments. In Text Analysis, we analysed the sentence lengths and audience reactions with ratings and extracted keywords with the TF-IDF metric.

Github
Project Image
Music Generation

In this project, we generated classical music with repeated melodic structures using a Long Short Term Memory (LSTM) Neural Network. Our model was trained using 405 tunes and is capable of generating music files (in ABC notation) with up to 2 piano instruments.

Github
Project Image
Gender Prediction with Song Lyrics

This is a natural language processing project involving lyrics to predict a singer’s gender. The model takes an input consisting of the lyrics of any size (in terms of number of words), and uses random forest with top 200 words based on tf-idf score, to predict gender of the singer.

GithubWebsite
Project Image
Omnomnom

A food recommender based off Burpple reviews. Having only textual reviews, sentiment analysis is done to assign a polarity score to each review, which is then aggregated for each food place. Based on user input, it matches and recommends the top 5 food places.

GithubWebsite
Project Image
ORCA Active Social Network Analysis Web App

Orca Active, a female athleisure brand (due for launch end 2020) worked together with SMU BIA, to come up with a project to help them identify customers of major influence via Social Network Analytics (SNA). The objective is to come up with something simple where everyone in the team can make sense of the data even if they do not have any data analytics/ science knowledge. Users can identify customers with major influence, allowing Orca Active to engage them in potential referral sales and partnership opportunities, as part of their marketing strategy.

GithubWebsite