Aleksandr Esin's Projects
No Regrets: A deep dive comparison of bandits and A/B testing
A-Bot - бот для торговли на Binance
Official Documentation for the Binance APIs and Streams
Official Documentation for the Binance Spot APIs and Streams
Critical difference diagram with Wilcoxon-Holm post-hoc analysis.
ChatGPT Native Application (Windows, Mac, Android, iOS, and Linux)
Github.com/CryptoSignal - #1 Quant Trading & Technical Analysis Bot - 2,100 + stars, 580 + forks
The Robot that trades futures on Binance
Python Cryptocurrency Portfolio
Dash - Reinventing Cryptocurrency
Deep NLP Course
DILMA: Differentiable Language Model Adversarial Attacks on Categorical Sequence Classifiers
Deep Learning for Time Series Classification
A few Python scripts to easily get data from the BitMEX API.
The official Python API for ElevenLabs Text to Speech.
The purpose of this project is to generate the methodology for prescriptive analytics of dynamic equipment using hybrid modeling. The methodology allows predicting a specific place of that malfunction and its numeric value of the malfunction parameter. As an example of a dynamic system, the Industrial Gas Turbine is investigated. This project aims to use generated data of the real malfunction parameters for Oil and Hydraulic subsystems using mathematical modeling and then to build the regression model for predicting the index technical state (ITS) of each of the malfunctions.
A bitcoin trading bot written in node - https://gekko.wizb.it/
A collection of useful .gitignore templates
gpt4all: run open-source LLMs anywhere
Official code release for "GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis"
Yandex Cup 2022 - ML RecSys
A fast fault diagnosis method for rolling bearings, based on extreme learning machine (ELM) and logistic mapping.
The PyTorch implementation of "Modeling Financial Time Series using LSTM with Trainable Initial Hidden States"
This LSTM is used to predict the rest useful lifetime of ball-bearings. Its programmed with Pytorch and uses the PRONOSTIA Dataset.
Using past price data and sentiment analysis from news and other documents to predict the S&P500 index using a LSTM RNN. Idea replicated from https://arxiv.org/abs/1912.07700 and https://arxiv.org/abs/1010.3003.
How to work through Markdown cells in Jupyter notebook.
Repository containing seminars from 2021 Machine Learning course at Skoltech