Skip to content
View ayushk2s's full-sized avatar
๐ŸŽฏ
Focusing
๐ŸŽฏ
Focusing

Block or report ayushk2s

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please donโ€™t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
Ayushk2s/README.md


Typing SVG

๐Ÿ”ญ Currently: Founder @ Amstos ยท Independent Researcher & Algorithm Developer ๐Ÿงช Independent research: systematic trading, quantitative finance, AI/ML, robotics & embedded systems ๐Ÿ“ Building in public โ€” documenting the journey through code, research, and experimentation


๐Ÿง  About Me

  • ๐Ÿ“ˆ Quantitative Researcher & Algorithm Developer focused on systematic trading and financial markets
  • ๐Ÿ Strongly focused on Python, quantitative research, backtesting & data analysis
  • ๐Ÿ’ป Building applications with Flutter, Dart, Firebase & REST APIs
  • ๐Ÿค– Exploring AI/ML, reinforcement learning, robotics & autonomous systems
  • โš™๏ธ Learning C++ for deeper systems and robotics development
  • ๐Ÿ“Š Researching momentum, volatility, correlation, portfolio construction and systematic strategies
  • ๐Ÿ—๏ธ Founder of Amstos โ€” a crypto portfolio analytics platform: read-only exchange analysis, 20+ risk/performance metrics, and an AI analyst that explains what's costing you money
  • ๐Ÿ”ฌ Conducting independent research in quantitative finance and algorithmic trading
  • ๐Ÿš€ Interested in building technology companies around AI, autonomous systems and advanced engineering

๐Ÿ› ๏ธ Tech Stack

Programming & Software

Area Technologies
Languages Python โ€ข Dart โ€ข C++
App Development Flutter โ€ข Firebase โ€ข REST APIs
Data & Research Pandas โ€ข NumPy โ€ข Data Analysis โ€ข Backtesting
Quant Finance Algorithmic Trading โ€ข Systematic Strategies โ€ข Portfolio Research
Development Git โ€ข GitHub โ€ข Linux
Cloud Firebase โ€ข Cloud-based application architecture

AI, Robotics & Hardware

๐Ÿค– Machine Learning & AI ย โ€ขย  ๐Ÿง  Reinforcement Learning ย โ€ขย  โš™๏ธ Embedded Systems ย โ€ขย  ๐Ÿ“ก IoT & Sensors ย โ€ขย  ๐Ÿš— Autonomous / Robotic Systems ย โ€ขย  ๐Ÿ›ฉ๏ธ Drones & Autonomous Systems ย โ€ขย  ๐Ÿ”ฌ Robotics, Aerospace & Advanced Engineering


๐Ÿ“ˆ Quantitative Research

One of my primary areas of work is systematic quantitative trading โ€” developing and backtesting algorithmic strategies using historical market data, quantitative signals, risk management, and portfolio-level analysis.

Research Areas

๐Ÿ“Š Momentum & trend following ย โ€ขย  ๐Ÿ”„ Multi-strategy portfolio rotation ย โ€ขย  ๐Ÿ“‰ Volatility targeting ย โ€ขย  ๐Ÿ”— Correlation-based strategies ย โ€ขย  ๐Ÿ’ฐ Portfolio construction ย โ€ขย  โš–๏ธ Risk/reward optimization ย โ€ขย  ๐Ÿ“ˆ Leverage-aware strategies ย โ€ขย  ๐Ÿงช Backtesting & statistical validation ย โ€ขย  ๐ŸŒŽ Multi-asset systematic investing ย โ€ขย  ๐Ÿช™ Crypto quantitative trading

I have researched strategies across equities and digital assets, with an emphasis on systematic decision-making rather than discretionary trading. Some of my historical backtests have produced 40%+ CAGR and ~63% CAGR results โ€” research/backtest figures, not claims of guaranteed or live performance.


๐Ÿงช Recent Research

  • CRYPTO-OPTIONS-LATENCY-ARB โ€” Tested whether Binance/Bybit BTC/ETH options lag Deribit enough to trade, via a four-gate test and 236K+ simulated trades. Verdict: no edge โ€” the lag is statistically real (p < 0.005) but worth ~$1/contract against ~$54 in realistic retail costs.
  • crypto-momentum-survivorship-audit โ€” Pre-registered audit of a crypto momentum strategy: Sharpe falls materially once survivorship-biased data is replaced with a proper point-in-time universe.
  • crypto-agent-reverse-engineering โ€” Reverse-engineered a third-party crypto trading agent, with an independent Binance perpetuals backtester and bias audits.

๐Ÿš€ Featured Projects

๐Ÿงฎ Amstos

A crypto portfolio analytics platform โ€” "Know why you're losing money." Read-only exchange access, 20+ metrics (Sharpe, Sortino, drawdown, VaR), behavioral-pattern detection, and an AI analyst that explains every number.

Focus: Portfolio analytics โ€ข Risk/performance metrics โ€ข Behavioral insights โ€ข AI-explained results

๐Ÿ“ˆ Crypto Algorithmic Trading

Quantitative trading research and algorithmic strategies for digital-asset markets.

Research includes: Momentum โ€ข Correlation โ€ข Trend signals โ€ข Volatility โ€ข Market regimes โ€ข Risk management โ€ข Automated strategy execution

๐ŸŒพ FarmYara

A smart agriculture application combining software, maps, and intelligent features for technology-driven agricultural solutions.

Technologies: Flutter Dart Firebase APIs

๐Ÿค– Robotics & Embedded Systems

Building and experimenting with hardware systems using microcontrollers, sensors, and actuators.

Exploring: ESP32 โ€ข Raspberry Pi Pico โ€ข Sensors โ€ข Motor control โ€ข Autonomous robots โ€ข IoT โ€ข Drone concepts


๐Ÿ”ฌ Research Interests

I'm particularly interested in the intersection of AI ร— Quantitative Finance ร— Robotics ร— Autonomous Systems.

๐Ÿง  Artificial Intelligence ย โ€ขย  ๐Ÿค– Autonomous Robotics ย โ€ขย  ๐ŸŽฎ Reinforcement Learning ย โ€ขย  ๐Ÿ“ˆ Quantitative Finance ย โ€ขย  ๐Ÿช™ Algorithmic Crypto Trading ย โ€ขย  ๐Ÿ›ฉ๏ธ Autonomous Drones ย โ€ขย  ๐Ÿ›ฐ๏ธ Aerospace Technology ย โ€ขย  ๐Ÿ›ก๏ธ Defense Technology ย โ€ขย  ๐Ÿงฌ Brain-Computer Interfaces ย โ€ขย  โš™๏ธ Intelligent Embedded Systems


๐Ÿ“š Current Learning

Python for quantitative research โ€ข C++ and systems programming โ€ข Machine Learning โ€ข Reinforcement Learning โ€ข Mathematics for AI & quantitative finance โ€ข Physics & engineering โ€ข Robotics and autonomous systems

My long-term goal is to combine mathematics, software, AI and engineering to build intelligent systems capable of solving complex real-world problems.


๐ŸŽฏ My Vision

"Build intelligent systems that amplify human potential."

I believe the most interesting technologies of the future will emerge from the combination of AI, automation, robotics, finance, and advanced engineering. Rather than simply using technology, I want to understand how it works, build it from the ground up, and eventually create companies around it.


โšก Current Focus

Quantitative Research       โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ
Algorithmic Trading         โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ
AI / Machine Learning       โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ
Software Engineering        โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ
Robotics / Embedded         โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ
C++ / Systems                โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ

๐Ÿ“Š GitHub Stats




๐ŸŒ Connect With Me

I'm building in public and documenting my journey through technology, quantitative research, AI, and entrepreneurship.

๐Ÿš€ Building. Researching. Experimenting.

One system at a time.

โญ If you find my projects interesting, feel free to explore my repositories and follow the journey.

Pinned Loading

  1. CRYPTO-OPTIONS-LATENCY-ARB CRYPTO-OPTIONS-LATENCY-ARB Public

    Do Binance & Bybit BTC/ETH options lag Deribit enough to trade? Live 3-exchange research: lead-lag stats, latency-aware paper trading, real fees. Verdict: no edge. 236k paper trades, 4 winners.

    HTML 2

  2. crypto-momentum-survivorship-audit-CRYPTO_XSMOM- crypto-momentum-survivorship-audit-CRYPTO_XSMOM- Public

    Pre-registered audit of a crypto cross-sectional momentum strategy. Backtest Sharpe 0.9 โ†’ 0.22 once the universe is built point-in-time with delisted coins; lost money on a sealed holdout. Includesโ€ฆ

    Python

  3. Best-Averaging-And-Leveraging Best-Averaging-And-Leveraging Public

    Proof and backtest code for optimal leverage sequencing in leveraged DCA strategies. Companion code for the paper: "Optimal Leverage Sequencing in Leveraged Dollar Cost Averaging: Theory and Multi-โ€ฆ

    Python

  4. crypto-agent-reverse-engineering crypto-agent-reverse-engineering Public

    Reverse-engineering a third-party crypto trading agent: realistic Binance perpetual backtester (fees, spread, funding, liquidation), look-ahead and bias audit, walk-forward, out-of-sample and Monteโ€ฆ

    Python 1

  5. LSCO LSCO Public

    This is my tried LSCO algorithm

    Python