Advanced AI for Traders & Asset Managers
A 16-day intensive bootcamp to master AI-driven trading strategies with hands-on projects, live mentorship, and real-world deployment skills.
Bootcamp Details
Program Duration
16 days
Nov 1 – Nov 16, 2025
Live Sessions
4 Days
with 4 Industry Experts
Projects
7 Projects
Guided Capstone Projects
Price
$1499
Refund issued on eligible grounds
Timings
4:00–9:00 PM IST
Session 1: 4–6 PM
Session 2: 7–9 PM
Seats
Limited Seats
Exclusive 16-Day Bootcamp
Why Join This Bootcamp?
Intense Learning
This bootcamp compresses years of trial-and-error learning into 2–3 intensive days
Market-Ready Debugging & Execution Hygiene
Cost functions, drift detection, risk monitoring, retraining cadence.
High ROI
Even quickly discarding weak ideas saves months of wasted effort.
Hands-On & Practical
Build, backtest, and deploy strategies with curated datasets, backtesting frameworks, and market APIs.
Exclusive Add-Ons
Gain access to ready-to-use code templates and support throughout the bootcamp
Schedule
Schedule
Day 1
Sat, 8 November
- Bootcamp structure, expectations, deliverables
- ML & AI in trading: use cases, scope, costs, risks
- Guided setup: idea → strategy logic → backtesting → live simulation
- Using AI copilots (ChatGPT, Copilot) to speed up coding and testing
- Agentic AI for automating research workflows
- Project 1: Workflow End-to-End using Co-Pilot
- Project 2: Agentic AI for Converting Ideas into Research Strategies
- Classification & Regression Trees vs. Neural Networks: Pros & cons, Market-specific examples like trees for SPX next-day return prediction and RNNs for predicting next-day SPX direction.
- How to Train a Neural Network: Backpropagation, stochastic gradient descent, Regularization techniques
- Different Neural Networks: MLP, RNN, LSTM
- Project 3: Build, Train, and Apply an RNN to Predict SPX Returns (with Chatbot Support)
Day 2
Sun, 9 November
- Data Preparation
- Time-Series Portfolio Architectures (LSTMs)
- Risk-Adjusted Optimization (Sharpe Loss)
- Optimization for Diversification
- Project 4: Diversification vs. Sharpe Ratio Comparison
- Discriminative vs Generative AI: Bayesian framing; why discriminative models are prediction-focused, while generative models can simulate entire datasets, Applications in trading
- Probabilistic Modeling of Time Series: Why financial data is noisy, non-stationary, and hard to model, Approaches: ARIMA → RNN, LSTM → attention-based models.
- The RNN Problem: slow training, vanishing/exploding gradients, difficulty handling long dependencies.
- Transformers to the Rescue: Transformer for sample-specific feature selection, Core architecture: queries, keys, values, Embedding, Positional encoding, Multi-head transformers.
- Project 5: Build, Fine-tune, and Apply the Poor Person’s Transformer for SPX Prediction
Day 3
Sat, 15 November
- Penalty for Trading Costs (Turnover)
- Management of Leverage and Asset Constraints
- Walk-Forward Optimization (WFO) Methodology
- Strategy Evaluation and Benchmarking
- Project 6: Executing the Full Constrained WFO Strategy
- BERT & FinBERT: pre-training vs fine-tuning
- Embeddings: text to numerical vectors
- Applications: news-driven signals, event studies, speeches
- Fine-tuning FinBERT for transcripts → sentiment scores → trading signals
- Risk management: overfitting, event clustering, multiple testing
- Project 7: Fed Speech Sentiment → SPY Backtest
Day 4
Sun, 16 November
7 Guided Projects
7 Guided Projects
Project 1
Project 2
Who should attend?
CMTs/Technical Analysts
Little/no ML background, seeking structured AI entry.
Traders & Asset Managers
Learn frameworks used in global trading desks.
Data Scientists/Analysts
ML knowledge, but limited market implementation.
Prerequisites
To ensure quality and peer learning, enrollment requires EPAT Certification of Excellence OR Passing an Entrance Test conducted by QuantInsti
What is EPAT?
The Executive Programme in Algorithmic Trading (EPAT) by QuantInsti is a 6-month online comprehensive certification programme with 120+ hours of live lectures and 150+ hours of recorded content, led by 20+ industry experts to provide hands-on experience for aspiring professional traders.
Faculty
Dr. Thomas Starke
AI & portfolio management pioneer
Dr. Ernest P. Chan
Global leader in quantitative trading & AI
Ishan Shah
Practitioner in ML-driven trading
Vivek Krishnamoorthy
Head of Content & Research at QuantInsti
Rekhit Pachanekar
Practitioner in ML-driven trading
Interested?
Testimonials
Some modules in this bootcamp overlap with these Quantra courses.
Hear from course learners!
Christian Alfaro
Customer Success Manager, Chile
Excellent course, i finally connect my RNN/LSTM knowledge with LLM
Veera Raghunatha Reddy Naguru
United Kingdom
Great course! Very detailed explanation about LLM's capabilities and their functionalities!
Artur Barreiros
Professor, Instituto Superior Técnico,Portugal
The concepts and ideas presented are excellent, and are well explained in the videos and comments available
Patricio Galvan
Spain
Very complete Course!
Nicolas Guillen
Spain
More than expected
Proof of Rigor
Deliverables
Jupyter notebooks + one-pager summary
Evaluation Rubric
Methodology (30%), Validation (25%), Results (25%), Risk/Execution (10%), Clarity (10%)
Learning Outcomes
Build and validate AI models, design robust workflows, and deploy strategies with confidence.
