Brain Markets: My Second Book on AI, Neuroscience, and the Future of Indian Markets

DOYR | Not financial/legal/tax advice. For educational purposes only.

---

If Right Brain Wins was about psychology, Brain Markets is about what comes next.

After writing the first book, I kept asking myself: "OK, right-brain trading helps me not lose money. But how do I actually gain an edge in a market where 95% of traders are fighting over the same scraps?"

The answer: AI + neuroscience + Indian markets.

Not the "AI will replace traders" hype. Not the "use GPT-4 to pick stocks" nonsense.

But something more practical: how to combine human intuition with machine intelligence to build a system that's better than either alone.

Brain Markets is that system.

---

What Is Brain Markets?

Brain Markets is a book that sits at the intersection of three fields:

1. Neuroscience — How the human brain makes decisions under uncertainty
2. Artificial Intelligence — How machines can augment human pattern recognition
3. Indian Markets — NSE, BSE, FII flows, retail participation, algo trading regulation

Core thesis: The future of trading is not human vs AI. It's human + AI.

And Indian retail traders who master this collaboration first will have an unprecedented edge.

---

Why I Wrote Brain Markets

The Gap

After Right Brain Wins, I started getting emails:

"Your framework helped me stop losing. But how do I actually WIN consistently?"

Good question. Psychology prevents losses. But wins require edge.

The Realization

Traditional edges are disappearing:

• Technical indicators = everyone uses them, no edge
• Fundamental analysis = institutional investors have 100x better data
• Tips = scams
• algo trading = expensive, not for retail

But there's one edge most retail traders ignore:

AI + human intuition = superhuman decision-making.

The Book's Promise

By the end of Brain Markets, you'll have:

Skill	Application
Local LLM sentiment analysis	Analyze 100 news headlines in 2 seconds
Vector search for patterns	Match current market to historical scenarios
Hybrid signal systems	Combine AI + technical + intuition
Mobile AI workstation	Run everything on Android/Termux
Backtesting AI models	Validate before live trading
Risk management	AI-augmented but human-decided

---

Chapter Breakdown

Part 1: The Neuroscience of Markets (Chapters 1-4)

Chapter 1: How Your Brain Trades (And Why It Fails)

• Amygdala hijack in markets
• Dopamine addiction to trading
• Confirmation bias in stock picking
• Loss aversion and its hidden costs

Chapter 2: The AI-Augmented Brain

• What AI does well: pattern matching, speed, data processing
• What humans do well: intuition, context, ethics
• The collaboration model: AI proposes, human disposes
• Case study: nse_ai_agent architecture

Chapter 3: Local LLMs for Trading

• Why cloud AI is wrong for real-time trading
• Ollama, Llama 3.2, Phi-3 on Android
• Building sentiment analyzer on your phone
• Privacy, latency, cost advantages

Chapter 4: Vector Search and Historical Memory

• ChromaDB for news pattern matching
• "This feels like 2020" → find what happened next
• Building your own market memory bank

Part 2: Building AI Trading Systems (Chapters 5-8)

Chapter 5: Data Pipeline for NSE

• Fetching live quotes, option chains, FII/DII
• Web scraping with ethical considerations
• NSE blocking and workarounds
• Building resilient data fetchers

Chapter 6: Sentiment Analysis Engine

• LLM prompt engineering for financial news
• Fallback systems when AI fails
• Scoring sentiment: 1-10 scale
• Combining with technical indicators

Chapter 7: Backtesting AI Strategies

• Why 99% backtest accuracy means nothing
• Walk-forward analysis
• Out-of-sample testing
• Avoiding overfitting

Chapter 8: Risk Management with AI

• AI-assisted position sizing
• Dynamic stop loss based on volatility
• Portfolio-level risk monitoring
• The human override rule

Part 3: The Indian Market Context (Chapters 9-12)

Chapter 9: NSE Specifics for AI Trading

• Lot sizes, expiry cycles, settlement
• FII/DII flow patterns
• PCR, OI, IV quirks in Indian markets
• Regulatory constraints (SEBI, algo trading rules)

Chapter 10: Retail Participation Boom

• Why 2024-2026 saw 3 crore new demat accounts
• What this means for market efficiency
• Opportunities for AI-augmented retail traders
• Risks of crowd behavior

Chapter 11: The Future of Indian Algo Trading

• SEBI's proposed regulations
• How local AI tools fit in
• Democratization vs institutionalization
• What changes in next 5 years

Chapter 12: Case Studies from nse_ai_agent

• 6-month live trading results
• What worked: LLM + momentum combo
• What didn't: LLM alone, far OTM options
• Performance attribution

Part 4: The Human Element (Chapters 13-16)

Chapter 13: When AI Fails

• Black swan events
• News that LLMs can't interpret
• When to override AI signals
• Building antifragile systems

Chapter 14: Ethics of AI Trading

• Market manipulation risks
• Fair access to AI tools
• Responsible AI development
• The case for open-source trading tools

Chapter 15: Building Your AI Trading Workflow

• Step-by-step setup on Termux/Android
• Choosing the right LLM for your phone
• Scheduling with cron
• Monitoring and maintenance

Chapter 16: The Next 10 Years

• Human-AI collaboration standard
• What skills matter most
• Why retail traders have advantage over institutions
• The future of work in trading

---

What Makes Brain Markets Different

Feature	Brain Markets	Other AI Trading Books
Context	Indian markets (NSE/BSE)	US markets
Platform	Termux/Android (free)	Desktop/cloud (expensive)
AI approach	Local LLMs (private, free)	Cloud APIs (costly, slow)
Transparency	Open-source code included	Black-box strategies
Honesty	Shows losses, limitations	Only shows wins
Accessibility	Written for retail traders	Written for quants/developers
Philosophy	Human + AI collaboration	AI replaces humans

---

Free Chapter: Building Your First LLM Sentiment Analyzer

From Chapter 6: Sentiment Analysis Engine.

---

The Problem

You're a retail trader. You have:

• ₹1 lakh capital
• A phone
• No Bloomberg terminal
• No team of analysts

Institutional traders have:

• 100+ analysts reading news 24/7
• AI systems processing 10,000 articles/minute
• Real-time sentiment feeds

Can you compete?

Yes. With local LLMs.

---

The Solution: 2-Hour Build

What you'll build:

• A script that fetches 20 NSE news headlines
• Sends them to a local LLM (Llama 3.2 3B)
• Gets back: BULLISH/BEARISH/NEUTRAL + score 1-10
• Combines with technical signals
• Sends Telegram alert

Time: 2 hours. Cost: ₹0.

---

Step 1: Install Ollama

# On Termux
pkg install ollama -y
ollama serve &
ollama pull llama3.2:3b

Step 2: Write the Analyzer

import requests
import json

class SentimentAnalyzer:
    def __init__(self, model="llama3.2:3b"):
        self.model = model
        self.url = "http://localhost:11434/api/generate"

    def analyze(self, headlines):
        prompt = f"""Analyze these Indian market news headlines for sentiment.

Headlines:
{chr(10).join(f"- {h}" for h in headlines)}

Respond with JSON:
{{"sentiment": "BULLISH/BEARISH/NEUTRAL", "score": 1-10, "reasoning": "2 sentences"}}"""

        response = requests.post(self.url, json={
            "model": self.model,
            "prompt": prompt,
            "stream": False,
            "options": {"temperature": 0.1, "num_predict": 150}
        }, timeout=30)

        result = json.loads(response.text)
        return json.loads(result['response'])

Step 3: Test It

analyzer = SentimentAnalyzer()

headlines = [
    "Nifty opens higher on strong FII inflows",
    "RBI keeps repo rate unchanged",
    "IT stocks drag on global concerns",
    "Q2 results: TCS beats, Infosys misses"
]

result = analyzer.analyze(headlines)
print(f"Sentiment: {result['sentiment']} ({result['score']}/10)")
# Output: Sentiment: BULLISH (7/10)

Step 4: Combine with Technicals

class HybridSignal:
    def __init__(self):
        self.sentiment_analyzer = SentimentAnalyzer()
        self.technical_weight = 0.7
        self.sentiment_weight = 0.3

    def generate_signal(self, technical_signal, headlines):
        sentiment = self.sentiment_analyzer.analyze(headlines)
        sentiment_score = sentiment['score'] / 10
        tech_score = technical_signal['confidence']

        final_score = (tech_score * self.technical_weight) + (sentiment_score * self.sentiment_weight)

        if final_score > 0.6:
            return "STRONG BUY"
        elif final_score > 0.3:
            return "BUY"
        elif final_score < -0.6:
            return "STRONG SELL"
        elif final_score < -0.3:
            return "SELL"
        else:
            return "HOLD"

---

The Book's Impact

Who's Reading It:

Reader Type	What They Get
Python developers	Complete code, architecture, deployment
Traders	AI augmentation without replacing judgment
Students	Career path in AI + finance
Open-source contributors	nse_ai_agent on GitHub
Curious minds	Future of markets, human-AI collaboration

---

How to Get Brain Markets

Formats Available:

Format	Price	Where
eBook (PDF)	₹249	optiontradingwithai.in
eBook (EPUB)	₹249	optiontradingwithai.in
Paperback	₹449	Amazon KDP
Audiobook	Coming soon	—

Bonus with Purchase:

• ✅ Complete nse_ai_agent source code
• ✅ 50+ Python scripts for NSE data
• ✅ Ollama setup guide for Android
• ✅ Private Telegram community
• ✅ Monthly live Q&A sessions

---

The Mission: Democratize AI Trading Tools

Right Brain Wins costs ₹199. Brain Markets costs ₹249. Combined: less than most people spend on one bad tip from a Telegram group.

Why?

Because information asymmetry is the biggest barrier in Indian markets. If you can't afford a ₹50,000 Bloomberg terminal or ₹2,000/month for Kite Connect, you shouldn't be excluded from professional-grade tools.

nse_ai_agent is free.
These books are affordable.
The knowledge should be accessible.

That's not a marketing strategy. That's a mission.

---

Connect With Shakti Tiwari

• Website: optiontradingwithai.in
• Dev.to: @shaktitiwari715-ai
• GitHub: @shaktitiwari715-ai
• X/Twitter: @shaktitiwari
• Telegram: @shaktitrade

---

Published on Dev.to | Tags: #brainmarkets #aitrading #nse #llm #termux #books #fintech

---

Author

Shakti Tiwari is an AI/quant trader and open-source developer from Chandigarh. He is the author of Right Brain Wins and Brain Markets, and maintains the nse_ai_agent project for Termux/Android. He writes about the intersection of AI, neuroscience, and Indian markets.