"All the models are wrong, but some are useful"
-- George Box

About Me

Hi, this is Pouya!

I am passionate about developing software solutions as well as continuous learning and applying new technologies/skills that can lead to efficient products.

I will soon graduate from my Master's of Science in Software Engineering (MSSE) at the Sharif University of Technology.

I have five years+ of experience in software development in Canada and Iran and try to build products with end-customer in perspective. I have grown teams from scratch and successfully mentored them and led them. I have used multiple programming languages and technology stacks, depending on the requirements. I believe in gaining a holistic picture of the product and its impact on consumers/clients.

In the following part, I'd like to share some of the projects I completed so far that I found interesting.

Featured Projects

Spark ML Infrastructure Design

A data pipeline which automates Ford Gobike data extraction from AWS S3 to MongoDB and connected to Spark to model bike demand.
(ETL, data pipeline, AWS, S3, MongoDB, SparkSQL, SparkML, Pyspark, )

SF Food Truck Map - Bites

A complete web product that shows dynamic food truck location and business information in SF.

(AWS, ETL, Flask, MongoDB, Google Analytics)

Playerunkown's Battleground gaming strategy visualization

A fully interactive visualization website to demonstrate gamer strategy in PUBG.

(D3, Plotly, Python, HTML)

Machine Learning and Statistics

Spam Classification

An Predictive model to classify whether an email is a spam or not

(python, boosting trees, numpy, XGBClassifier)

Movie Recommendation

A collaborative filtering system to potential predict movie rating for a viewer.

(matrix factorization, stochastic gradient descent optimization, numpy)

Handwritten Digit recognition

A vanila version of Neural Network to classify digits from images. Trained on MNIST dataset.

(Pytorch, AWS, neural network tuning, )

Canadian Bankruptcy Rate Prediction With Time Series

Time Series forecast of Canadian bankruptcy rate with macroeconomic indicator.

(R, Holt-Winters, SARIMA, VARX)

Iowa House Price Prediction With Linear Regression

An regression analysis and business report of house price prediction in Iowa.
(R, OLS, Lasso, Ridge, Elastic Net)

US Domestic Flight Delay Prediction

An Random Forest model to predict a given flight's delay rate.
(Python, feature engineering, model interpretation)

Stay Connected