martinmashalov Goto Github PK
Name: Martin Mashalov
Type: User
Company: Peak Real Estate LLC
Location: New York, NY
Name: Martin Mashalov
Type: User
Company: Peak Real Estate LLC
Location: New York, NY
Derived neural network code from scratch to investigate inner nature of these deep learning models. Created a Vanilla ANN from scratch and used mathematical modeling concepts to create CNN model to classify handwritten digits.
Using vectorized operations and optimization theory to identify arbitrage in basketball betting at faster speeds to beat the bookmakers.
Bikeshare project with Udacity data science course. First project with pandas and numpy in Python data science.
Backtesting software for intraday and daily timeframe SARIMAX forecasting model. Capable of forecasting on any asset class with backtesting capability across various parameter sets customizable by the user.
Bison Options Futures HFT. Predicts directional pricing movement in SPY and provides indicator data to assist algorithmic trading engine.
Streamlined python package API providing developers the ability to create custom algorithmic and quantitative trading strategies to drive actionable returns.
All experiments I have done with computer vision technology, including OpenCV, YOLO, CNNs, Attention, Segmentation, Object Detection, and more. For educational purposes only.
Whatsapp chatbot that allows users to interact with Covid-19 data, find nearest testing centers, and discover credible organization for more information.
A Covid19 Data Dashboard built with Javascript, HTML, CSS with the React framework. Displays Covid19 statistics regarding the pandemic to increase public awareness about the statistics.
WebAPI and Data Collection for COVID-19 testing location across all 50 U.S States. Data Mining accomplished with Python scripts from various websites and official sources.
Predicting asset prices' directional movements based on implied volatility of price action. This experiment was performed on SPX index fund with VIX as implied volatility reference.
R notesbooks used for analysis of actuarial data and to make decisions about portfolios of policyholders.
Neural Architecture Search experimentation on various image recognition datasets (MNIST, FashionMNIST, FOOD101). The concepts of NAS are implemented in PyTorch and Microsoft NNI including hyperparameter tuning, architecture search and compression, and extensive feature engineering.
Reinforcement learning agent for Othello board game implemented in AI. All code is written from scratch to investigate inner workings of RL algorithms. Project was done in completion of Columbia University SHAPE2020 Advanced Computer Science Course.
Emotional Intelligence and Music data analysis project. Consisted of searching for Pearson R correlations, Chi squared testing, and extended data visualization.
Research on using markov decision processes in combination with decision tree classifiers to predict outcomes of NFL Football and ATP/WTA Professional Tennis matches and generate descriptive and actionable analytics in the process.
Sports API collecting all data on matches, players, teams, and live odds based on the NFL, NBA, MLB, and NHL leagues.
Created simple Svelte application to record user feedback and simulate writing comments and the liking feature. First experiment with frontend frameworks and web development.
Learned basics of Svelte components, frontend framework usage, as well as review on Javascript concepts used in future Svelte applications.
Technical Analysis (TA) investigation with Python. Moving averages included as well as outlier detection using signal processing and smoothing. Included as well is market characteristic detection with hurst exponent analysis.
Screen for stocks in the SPY500 that yield potentially actionable price pattern setups for options trading.
Predicting future VIX movements using forked repository from @maylathant. Investigation on VIX price action and predictive modeling in order to aid in risk management on SPX index fund.
Generative voice cloning model using TTS synthesis with state-of-the-art Zero-Shot Multi-Speaker functionality. An web api built with the YourTTS TTS model to clone and generate realistic audio waves
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.