Quant AI Trading Lab — Algorithmic Trading Course

Why this course

Most traders learn trading
the hardest possible way.

Trial and error. Real money. Emotional decisions. Years of losses before any clarity. This course reverses that process entirely — you build the evidence first, then trade.

Backtest before you risk money

Every strategy gets validated on historical data with realistic assumptions before a single rupee goes live. You trade with evidence, not hope.

Skip the 3-year learning curve

What takes most traders 3 years of painful trial and error to discover, this course condenses into a structured, systematic learning path.

Build systems, not instincts

Learn to replace gut decisions with data-driven systems. Your strategies become replicable, improvable, and automatable — not locked in your head.

Three learning tracks

One course. Three paths.
Built for where you are.

Choose the track that matches your current level. Each track has its own module flow, projects, and live session focus — but all converge on the same destination: systematic, data-driven trading.

Zero to Systematic Trader

You have no trading experience. That’s actually an advantage — you won’t have bad habits to unlearn. You’ll start with Python, understand markets structurally, and learn to validate ideas before you ever risk money live.

You will graduate able to

Write a Python-based backtest, validate a strategy across market conditions, understand its edge, and deploy it live with a proper risk framework — without ever having gone through painful trial and error.

No prior trading experience needed

Basic Python comfort helpful but not required

Serious about building a systematic approach from scratch

MOD 01

Markets, instruments & how they really work

· Foundation

+

How financial markets are structured — exchanges, order books, price formation

Asset classes — equities, futures, options, crypto: how they differ and why it matters for strategy

How prices move — supply/demand, market participants, institutional vs retail behaviour

Reading charts and data — OHLCV data, timeframes, what each tells you

The trading lifecycle — idea → backtest → validate → paper trade → live deploy

ConceptualMarket structureNo code yet

Mini-project: Document how a specific stock/futures contract moves over 30 trading days. Identify patterns manually before learning to code them.

MOD 02

Python for trading — from zero to functional

· Programming foundation

+

Python basics for data work — variables, loops, functions, data structures

Pandas & NumPy — working with price data, calculating returns, rolling windows

Fetching market data — Yahoo Finance, NSE, broker APIs: pull real data for analysis

Visualising price data — matplotlib, plotly: charts that actually help you see patterns

Building your first indicator — code a moving average, RSI, and VWAP from scratch

PythonPandasNumPyPlotting

Project: Pull 1 year of NIFTY data, calculate a 20-day and 50-day moving average, plot them, and write a simple signal generator in Python.

MOD 03

Your first backtest — building the engine

· Core skill

+

What a backtest actually is — simulating trades on historical data with realistic rules

Building a backtesting loop — entry signals, exit conditions, position management in pure Python

Adding realistic costs — slippage, brokerage, STT, spread: why ignoring these is fatal

Performance metrics — Sharpe ratio, max drawdown, win rate, profit factor: what each actually means

BacktestingBacktraderPerformance metrics

Project: Backtest a simple moving average crossover strategy on NIFTY 50. Compare results with and without realistic transaction costs. Interpret the Sharpe and drawdown.

MOD 04

Strategy validation — is this real or just noise?

· Critical thinking

+

The 3 hidden biases — look-ahead bias, survivorship bias, data snooping: how to detect each

Overfitting vs robustness — why a great backtest often means a terrible live strategy

Out-of-sample testing — train/test split, walk-forward validation: the only honest test

Monte Carlo simulation — stress-testing your strategy across 1000 random scenarios

Market phase testing — does your strategy work in trending, ranging, and volatile markets?

ValidationWalk-forwardMonte CarloBias detection

Project: Take your MA crossover backtest. Apply walk-forward validation. Run 500 Monte Carlo simulations. Write a one-page verdict: is this edge real?

MOD 05

Risk management — protecting capital is strategy

· Risk systems

+

Position sizing models — fixed fraction, Kelly criterion, volatility-adjusted sizing

Drawdown management — max drawdown rules, daily loss limits, circuit breakers

Portfolio-level risk — correlation between strategies, sector exposure, margin management

Building a risk dashboard — real-time P&L, exposure, and risk metric monitoring in Python

Risk managementPosition sizingKelly criterion

Project: Build a Python risk calculator. Input: strategy returns. Output: recommended position size, stop-loss levels, and daily loss limit based on your account size.

MOD 06

Going live — paper trade to real deployment

· Live trading

+

Paper trading setup — testing your system in real market conditions without real money

Broker API integration — connecting Python to Zerodha Kite, Fyers, or Upstox APIs

Order execution logic — market vs limit orders, slippage control, partial fills

Monitoring & alerts — building a dashboard to track live strategy performance

The go-live checklist — 20 things to verify before switching from paper to live capital

Live tradingZerodha Kite APIOrder executionMonitoring

Capstone: Deploy your validated strategy to paper trading for 4 weeks. Compare paper results to backtest expectations. Document discrepancies and their causes.

Emotional to Systematic Trader

You’re already trading but your results are inconsistent. You know what to do — but you don’t do it. The problem isn’t discipline, it’s that you’re relying on intuition in a game that requires systems.

You will graduate able to

Take your existing approach, backtest it properly, identify what actually works and when, build tools that eliminate emotional decisions, and automate the parts that consistency requires.

6+ months of active trading experience

Struggling with emotional biases and inconsistency

Some Python familiarity helpful but not required

MOD 01

Diagnosing your current trading — what’s actually broken

· Self-audit

+

Trade journal analysis — mining your own trade history for patterns and hidden biases

Identifying your actual edge — separating what works from what you think works

Where emotion creeps in — FOMO entries, revenge trades, premature exits: quantifying the cost

The rules you break — why having rules and following them are completely different problems

Trade analysisSelf-auditPsychology

Project: Pull your last 6 months of trades. Calculate P&L by setup type, time of day, and market condition. Find your top 3 money-losing patterns.

MOD 02

Python for traders — build tools, not just run code

· Tool-building

+

Python accelerated for traders — skip the basics, focus on what you’ll actually use daily

Building a screener — scan 500 stocks for your specific setup criteria automatically

Charting with context — interactive charts that overlay your trade markers on historical price

Alert systems — Telegram/WhatsApp alerts when your criteria trigger, so you never miss a setup

PythonScreenerAlertsDashboard

Project: Build a stock screener for your specific setup. Add a Telegram alert that messages you when conditions are met during market hours.

MOD 03

Backtesting your own strategy — converting intuition to rules

· Strategy formalisation

+

Converting your trading approach to code — formalising fuzzy rules into precise, testable logic

Backtesting with real costs — adding brokerage, slippage, and impact to see true performance

Bias detection on your own strategy — look-ahead bias, survivorship bias, data snooping

Walk-forward validation — testing robustness on out-of-sample periods your strategy has never seen

Market phase mapping — when does your strategy work? When should you sit out?

Strategy formalisationBacktestingWalk-forward

Project: Take your #1 trading setup. Code it precisely. Backtest 2 years. Apply walk-forward. Find the 3 market conditions where it fails. Build a phase filter.

MOD 04

Building systematic analysis tools

· Analysis systems

+

Building a trade management dashboard — live P&L, open positions, risk exposure in one view

Pre-market analysis automation — scripts that prepare your watchlist and key levels before market open

Post-trade analysis system — automatically log trades, tag outcomes, and generate weekly reports

Market regime detector — automated signal that tells you which mode the market is in today

DashboardPre-market toolsTrade logging

Project: Build a pre-market morning script. Runs at 9:00 AM. Outputs: market regime, your watchlist setups, key support/resistance, and max risk for the day.

MOD 05

Risk systems — from gut-feel to data-driven

· Risk architecture

+

Replacing emotional position sizing — volatility-based and Kelly-based sizing that adapts to market conditions

Drawdown-based circuit breakers — automated rules that reduce size or stop trading after defined loss levels

Daily and weekly risk limits — coding hard limits into your system so emotion never overrides them

Risk managementAutomationPosition sizing

Project: Recode your position sizing from intuition-based to volatility-adjusted. Backtest the difference in drawdown profile over 2 years.

MOD 06

Automation — from semi-manual to fully systematic

· Automation

+

Broker API connection — Zerodha Kite, Fyers, Upstox: connecting Python to your broker

Semi-automation — alert fires, you confirm, system executes: human-in-the-loop model

Full automation — signal to execution without manual intervention: when and how to do this safely

Running strategies on a server — VPS setup, scheduling, monitoring, error handling

API integrationAutomationVPSKite API

Capstone: Automate your top strategy end-to-end. Signal generation → risk check → order execution → trade log → P&L report. Run on paper for 30 days.

Automate & Scale Your Edge

You have a proven edge. You understand markets. What you need now is to turn your approach into a robust, automated system that scales without you being glued to the screen.

You will graduate able to

Refine your strategy with advanced validation, automate it fully using broker APIs, run multiple strategies simultaneously, and build the infrastructure to scale your trading operations professionally.

2+ years of trading experience with consistent results

Has a defined edge that works but isn’t yet automated

Some Python/coding experience preferred

MOD 01

Advanced strategy validation — beyond the basic backtest

· Rigorous testing

+

Walk-forward optimisation — dynamic parameter optimisation that adapts as markets evolve

Regime-conditional backtesting — testing performance separately in trend, range, and volatile regimes

Monte Carlo stress testing — 10,000 simulations to find max realistic drawdown and ruin probability

Transaction cost sensitivity analysis — how much does slippage need to increase before the strategy breaks?

Strategy capacity analysis — how much capital can this strategy actually absorb without degrading?

Walk-forward optimisationMonte CarloRegime analysis

Project: Full validation report on your primary strategy. 10,000 Monte Carlo runs, regime breakdown, capacity analysis. Present as a professional tearsheet.

MOD 02

Strategy refinement — finding the hidden performance leaks

· Optimisation

+

Execution quality analysis — measuring slippage vs modelled costs, finding where performance leaks

Entry and exit optimisation — data-driven refinement of entry timing and exit mechanics

Filter stacking — adding market regime, volatility, and correlation filters without overfitting

Strategy ensembling — combining multiple strategies to reduce drawdown and smooth equity curve

OptimisationExecution qualityEnsembling

MOD 03

Full automation architecture — production-grade systems

· Engineering

+

Production system design — separating data, signal, risk, and execution layers cleanly

Advanced broker API integration — Zerodha, Fyers, Upstox: real-time data feeds, WebSocket connections

Error handling and resilience — what happens when API fails, network drops, order rejects

Multi-strategy execution — running multiple uncorrelated strategies simultaneously with shared risk budget

VPS deployment & scheduling — 24/7 uptime, cron jobs, watchdog processes, auto-restart logic

System architectureWebSocketMulti-strategyVPS

Project: Deploy 2 uncorrelated strategies on a VPS with shared risk management, automated error recovery, and a live Telegram monitoring bot.

MOD 04

Scaling operations — from one to many strategies

· Scale

+

Portfolio-level risk management — capital allocation across multiple strategies, correlation management

Strategy pipeline — systematic process for researching, testing, approving and deploying new strategies

Performance attribution — which strategy, which regime, which time period is generating your P&L?

Operational infrastructure — data storage, backup systems, trade record-keeping, tax-ready reporting

Portfolio managementAttributionInfrastructure

MOD 05

Advanced quant methods — taking your edge further

· Advanced

+

Statistical arbitrage basics — pairs trading, cointegration, mean reversion frameworks

Factor-based models — momentum, mean reversion, volatility: building multi-factor strategies

Machine learning for signals — using ML for signal generation without the overfitting traps

Options strategy automation — systematising options selling, hedging, and adjustment rules

Stat arbFactor modelsML signalsOptions

Capstone: Research, backtest, validate, and deploy a brand-new strategy that you’ve never traded before — entirely from scratch using the full pipeline taught in this track.

What you’ll learn to use

The professional trading tech stack

Every tool you learn in this course is used by professional quant traders. No toy examples — real tools, real data, real markets.

Language

Python 3.x

The primary language for all strategy development, backtesting, and automation in this course.

Data

Pandas & NumPy

Core libraries for price data manipulation, return calculation, and statistical analysis.

Backtesting

VectorBT

High-performance vectorised backtesting for rapid strategy iteration and parameter studies.

Data Source

NSE / Yahoo Finance

Indian market data from NSE directly and Yahoo Finance for historical OHLCV data.

Broker API

Zerodha Kite API

Live order execution, real-time market data feed, and position management via Python.

Broker API

Dhan

Alternative broker APIs for live trading with WebSocket real-time data support.

Visualisation

Plotly / Matplotlib

Interactive strategy performance charts, drawdown visualisation, and trade analysis plots.

The difference

How most traders learn
vs how you will.

The old way

×Open account, deposit money, start trading

×Learn by losing real capital

×Follow tips, signals, and YouTube gurus

×Trade on intuition and “chart feel”

×No idea if your strategy actually has an edge

×Panic when markets move against you

×Change strategy after every losing streak

×3–5 years of pain before any clarity

The Quant-Astra way

✓Backtest first, validate, then go live

✓Learn on historical data — zero capital at risk

✓Build your own edge based on your own data

✓Trade with rules your system follows automatically

✓Know your edge, its limits, and when it fails

✓Your risk system controls position size, not fear

✓Drawdowns are expected and planned for in advance

✓Structured path from idea to live systematic trading

What you’ll build

Graduate with real deliverables

Every track ends with live projects you actually built — not certificates, not theory. Things you can deploy immediately.

01

A validated, bias-free backtest

A strategy backtest you can actually trust — walk-forward validated, bias-corrected, stress-tested with Monte Carlo, and phase-mapped across market conditions.

02

A working Python trading toolkit

A screener, alert system, pre-market script, trade logger, and performance dashboard — tools built in Python that you’ll actually use daily.

03

A live-deployed automated strategy

Your strategy connected to a broker API, running on a VPS, with real-time monitoring, automatic risk controls, and Telegram notifications. Running 24/7 without you.

04

A professional risk framework

A position sizing model, drawdown rules, daily loss limits, and a personal risk dashboard — all coded so your system enforces discipline automatically.

05

A strategy tearsheet

A professional performance report including Sharpe, Sortino, max drawdown, win rate, regime breakdown, and capacity analysis. The kind hedge funds use internally.

06

A research pipeline

A repeatable process for ideating, backtesting, validating, and deploying new strategies. So you never stop improving — even after the course ends.

Your Instructor

Shashank Khatri

CEO @ Quant Astra
CFA Level III Cleared

8+ years building and deploying automated trading systems in Indian equity and derivatives markets.

What I Do

Live trading: Systematic options strategies, stock selection, derivatives execution

Systems: API-driven multi-broker execution frameworks using Python

Research: Quantitative analysis of market cycles, volatility behavior, greeks, and strategy robustness

Teaching: Courses in quantitative trading, systematic validation, and live strategy deployment

Why I Teach

“Most traders lose money not because they lack discipline—they lose because they lack clarity. Their backtests lie. Their strategies work in one phase and fail in another. They don’t know why.”

I created Quant AI Trading Lab to close this gap. Every trader deserves to understand the five hidden biases destroying their live returns. Every strategy deserves honest validation before live capital is deployed.

Credentials & Certifications

CFA Program: Level III cleared | 90+ percentile in Level II

EPAT Certificate: QuantInsti algorithmic trading (Python, backtesting, quantitative techniques)

NISM Series VIII: Equity derivatives certified

8 Years Trading: 3 years building automated systems | Active proprietary trader

Currently: Running proprietary trading desk + Training serious traders in systematic validation and deployment.

Choose your track

Join the course.
Pick your path.

All three tracks include live sessions, project reviews, lifetime access to recordings, and direct access to the instructor. Contact us to confirm the next batch date and seat availability.

Track 01

Zero to Systematic Trader

For freshers with no trading experience who want to learn the right way — backtest first, trade second.

✓6 modules,

✓Python from absolute zero

✓Full backtesting curriculum

✓Live deployment to broker API

✓6 hands-on projects

✓Lifetime session recordings

Enquire & enroll →

Frequently asked questions

Do I need prior coding or trading experience?+

For Track 01 (Fresher), no experience in either is needed — we start from scratch. For Track 02, some trading experience is required. For Track 03, solid trading experience and some Python comfort is recommended. Each track is designed for its audience.

Are the sessions live or pre-recorded?+

All sessions are live — you attend in real time, ask questions, and work on problems interactively. Recordings of every session are provided so you can revisit anything at any time. There is no pre-recorded-only option.

Which broker API will I learn to use?+

Primary focus is on Zerodha Kite API, which is the most widely used in India. We also cover Fyers and Upstox APIs. The concepts transfer to any broker API — once you learn one, the others follow the same patterns.

Will I actually deploy a live strategy by the end?+

Yes — that is the capstone of every track. You will have a validated strategy connected to a broker API, running on a VPS with monitoring and risk controls. The capstone is done on paper trading first, then you control when to switch to live capital.

How long is the course and what is the time commitment?+

The full course runs 10–14 weeks depending on the track. Sessions are typically 2–3 times per week. Expect 4–6 hours per week for sessions and project work. The pace is designed to fit around working hours — most students are employed or running businesses.

Is this focused on Indian markets specifically?+

Yes. All examples use NSE equities, NIFTY futures, and Indian options contracts. Broker API integrations are all India-focused (Zerodha, Fyers, Upstox). The regulatory context, taxes, and market microstructure are all Indian — not adapted from US courses.

Learn to trade
the right way.
From day one.

Most traders learn trading
the hardest possible way.

One course. Three paths.
Built for where you are.

Zero to Systematic Trader

Emotional to Systematic Trader

Automate & Scale Your Edge

The professional trading tech stack

How most traders learn
vs how you will.

The old way

The Quant-Astra way

Graduate with real deliverables

8+ years building and deploying automated trading systems in Indian equity and derivatives markets.

What I Do

Why I Teach

Credentials & Certifications

Join the course.
Pick your path.

Frequently asked questions

Stop learning trading
the expensive way. Start here.

Learn to tradethe right way.From day one.

Most traders learn tradingthe hardest possible way.

One course. Three paths.Built for where you are.

Zero to Systematic Trader

Emotional to Systematic Trader

Automate & Scale Your Edge

The professional trading tech stack

How most traders learnvs how you will.

The old way

The Quant-Astra way

Graduate with real deliverables

8+ years building and deploying automated trading systems in Indian equity and derivatives markets.

What I Do

Why I Teach

Credentials & Certifications

Join the course.Pick your path.

Frequently asked questions

Stop learning tradingthe expensive way. Start here.

Learn to trade
the right way.
From day one.

Most traders learn trading
the hardest possible way.

One course. Three paths.
Built for where you are.

How most traders learn
vs how you will.

Join the course.
Pick your path.

Stop learning trading
the expensive way. Start here.