Nasser Bashkeel

Data Scientist
MSc Bioinformatics

About Me

I am continually in search for underlying patterns that illuminate hidden connections between seemingly disparate entities. My passion lies in uncovering solutions to challenging problems and turning complex information into clear-cut, actionable statements.

Data Science/ML researcher with a lifelong learning mentality
Storytelling enthusiast using statistics and data visualization
Brazilian jiu-jitsu player | Dungeons & Dragons nerd | Home chef

Download my cv or contact me if you’d like to share ideas.

What I Bring to the Table

Machine Learning

Advanced statistical models in Python and R

Statistical Inferences

Deduction of underlying probability distributions

Creative Problem-Solving

Merging scientific methods & divergent thinking

Data Visualization

Mastery of ggplot2, matplotlib, and Tableau

Text Mining

Sentiment analysis of complex customer data

Advanced SQL Querying

End-to-end pipelines for easy data analysis

Featured Projects

Here are a few select projects I’ve completed. The code can also be found on my github account

Pet Adoption Time 2.0 - More than Tabular Data

Vast improvement and refactoring of the previous Pet Adoption Time project. Incorporated image feature extraction, image metadata, entity sentiment, and text mining to the initial model

Skills: Python, Keras, LightGBM, Google Vision, Google NLP, Convolutional Neural Network, TF-IDF

Sonic Strata

Front-end web app visualizing and analyzing artists’ musical audio features through Spotify’s Web API. Identifies the most unique and the most ordinary tracks for an artist and provides recommendations for other similar songs
(Note: Please allow a few moments for Heroku to spin up the initial dyno)

Skills: Python, App Development, CSS, API, Data Visualization

Neural Style Transfer

Extracts deep image feature representations and merges the content of one image with the style of a second images

Skills: Python, TensorFlow, Computer Vision, Convolutional Neural Network

Breakfast MBA

Increasing profitability of a bakery through Association Rule Learning

Skills: R, Association Rule Learning, Market Basket Analysis

Pet Adoption Time

Predicting pet adoption time using a decision tree ensemble model

Skills: Python, Supervised Ensemble Learning, XGBoost, Decision Trees, χ2 Analysis, EDA

NLP & Sentiment Analysis

Predicting polarity of user reviews through text mining of IMDB reviews without NLTK’s SentimentAnalyzer library

Skills: Python, NLP, Sentiment Analysis, Text Mining

Predicting House Prices in Ames, Iowa

An XGBoost ensemble model predicting house prices of the Boston real estate market

Skills: Python, Imputation, Regression, Feature Engineering, XGBoost, Ensemble Models

Titanic Survival Prediction

Predicting survival of passengers aboard the Titanic using binary classification machine learning

Skills: Python, EDA, Feature Engineering, Imputation, Classification, Neural Networks

Recent Publications

Human gene expression variability and its dependence on methylation and aging

Gene expression variability in the human population is likely to be important in tissue development and identity, methylation, and in natural biological aging. The expression variability of a gene is an important functional characteristic of the gene itself and the classification of a gene as one with Hyper-Variability or Hypo-Variability in a human population or in a specific tissue should be useful in the identification of important genes that functionally regulate development or disease.

Bashkeel et al. BMC Genomics 20, 941 (2019)

Continue Reading Full PDF text

Blog

A collection of cool things I’ve worked on for my personal enjoyment >>