Data Scientist and Software Developer in San Jose, United States

This is an automated machine learning tool that uses machine learning and data mining techniques for preprocessing data and choosing the machine learning model automatedly for a given problem.

I used a meta-learning strategy to select the most appropriate algorithm and its parameters. This project is implemented in Spark and the Scala programming language to handle big data.

This project aims to predict the UK's gas demand using several techniques, such as feature engineering and data augmentation.

First, I implemented an extreme day detection module to label the data as extreme or not extreme. An oversampling method helped enhance extreme days because they were a small portion of the data. I also implemented a dynamic weighted ensemble model using a multilayer perceptron (MLP) and a linear regression model to consider both linear and non-linear trends.

The goal of the project is to predict stock prices over the Frankfurt Stock Exchange, including those for BMW and Daimler. I built RNN, GRU, and LSTM models in PyTorch because it is a time series problem.

In this project, I mainly implemented various generative networks, and their components to perform unsupervised learning for the generation of new data samples (images) and, the denoising of images.

This project aims to predict the market prices of products in several domains using pictures and their corresponding market values. I trained a convolutional neural network to predict the price of a given product using Python and Keras.

This is a parental control tool consisting of content filtering, usage time controlling, usage management (for allowing/blocking a set of software types), and monitoring to watch and report user activities. It is an open-source project developed for Pardus, a Linux distribution, using PyQt, Python, and Bash.