← Back to Blog

Building a $0.50/Month Market Intelligence Platform on AWS

December 1, 2025 • 12 min read

How I built a professional-grade financial analysis system for tracking market trends for less than the cost of a coffee

The Challenge

I wanted to build a market intelligence platform for tracking market trends that could:

Track 214 stocks across all major sectors
Generate market commentary twice daily
Send professional HTML emails to subscribers
Provide real-time technical analysis via web interface
Run Monte Carlo simulations for price projections
Cost less than a Netflix subscription

Traditional approaches would cost $200-500/month. Using AWS serverless architecture and Kiro (AWS AI assistant), I built it for $0.50.

Architecture Overview

The Serverless Stack

Data Layer: DynamoDB (5 tables, 13,500+ records)
Price history, technical features, projections, cache, signals

Compute Layer: AWS Lambda (10+ functions)
Data ingestion, feature engineering, AI analysis, email delivery

AI Layer: Amazon Bedrock (Claude 3 Haiku)
Generates institutional-quality market commentary

Orchestration: EventBridge
Runs twice daily: 7am (pre-market) and 5pm (post-market)

Frontend: S3 + CloudFront
Static website with interactive charts

Messaging: Amazon SES
HTML emails with market analysis and trade signals

The Daily Pipeline

Morning Flow (7:00-8:00 AM ET)

7:00 AM - Data Ingestion
Fetch 214 tickers from Yahoo Finance, store OHLCV data in DynamoDB. Takes 60 seconds, costs $0.0001

7:10 AM - Feature Engineering
Calculate 20+ technical indicators: RSI, moving averages, volatility, returns, Bollinger Bands, MACD, ATR. Process 124 tickers in 30 seconds.

7:15 AM - AI Analysis
Claude 3 Haiku generates structured JSON (market overview, insights, levels) and professional prose letter (400+ words). Uses only observable price data - no speculation.

8:00 AM - Email Delivery
Send HTML emails to subscribers with AI commentary, technical levels, trade signals, and unusual activity.

Evening Flow (5:00-5:20 PM ET)

5:00 PM - Refresh data with market close prices
5:10 PM - Recalculate features
5:15 PM - Generate updated analysis
5:20 PM - Run Monte Carlo simulations (90-day projections)

Signal Generation Logic

Multi-Factor Scoring System

Signals are generated by combining multiple technical indicators into a composite score:

Momentum Signals (40% weight)

RSI: Oversold (<30) = bullish, Overbought (>70) = bearish
MACD: Crossover above signal line = bullish, below = bearish
Price vs MA20: Above = bullish momentum, below = bearish

Trend Signals (30% weight)

MA20 vs MA50: Golden cross = bullish, death cross = bearish
Price position: Above MA50 = uptrend, below = downtrend
Trend strength: Measured by distance from moving averages

Volatility Signals (20% weight)

Bollinger Bands: Price at lower band = oversold, upper band = overbought
ATR expansion: High volatility = caution, low volatility = potential breakout
Volatility percentile: Compare current to 90-day range

Volume Confirmation (10% weight)

Volume vs 20-day average: Above = conviction, below = weak signal
Price-volume divergence: Rising price + falling volume = warning

Signal Classification

Composite scores are translated into actionable signals:

Strong Buy: Score > 70, multiple indicators aligned, volume confirmation
Buy: Score 50-70, positive momentum, trend support
Hold: Score 30-50, mixed signals, wait for clarity
Sell: Score 10-30, negative momentum, trend breakdown
Strong Sell: Score < 10, multiple bearish indicators, high conviction

Signal Validation

Before sending signals, the system validates:

Data Quality: Minimum 90 days of price history required
Liquidity Filter: Only stocks with avg volume > 500K shares
Volatility Check: Flag extreme moves (>3 standard deviations)
Correlation Analysis: Compare to sector ETF for context

Signals are tracked in DynamoDB with timestamps, allowing performance measurement and backtesting.

Key Technical Decisions

1. Why Serverless?

Cost Efficiency

Lambda: Pay per 100ms of execution
DynamoDB: Pay per read/write
No idle server costs

Auto-Scaling

1 user or 10,000 users - same code
No capacity planning
No server management

Reliability

AWS manages infrastructure
Built-in redundancy
99.99% uptime SLA

2. Why DynamoDB Over RDS?

Performance: Single-digit millisecond latency, no connection pooling issues, scales automatically

Cost: On-demand pricing at $0.09/month for my workload vs RDS t3.micro at $15/month minimum

Simplicity: No database maintenance, backups, or version upgrades

3. Why Claude 3 Haiku?

Quality: Generates institutional-grade analysis, follows complex prompts precisely, understands financial terminology

Cost: $0.25/1M input tokens, $1.25/1M output tokens. My usage: $0.14/month

Speed: Responds in 2-3 seconds, fast enough for real-time API

The AI Prompt Engineering

Challenge: Data-Only Analysis

I constrained Claude to use ONLY observable price data:

CRITICAL CONSTRAINT: Use ONLY the data provided. 
Do not reference any external information, news, 
earnings, analyst actions, or events not directly 
observable in this price data.

Prompt Refinement

Iterated through 5 versions to achieve:

Precise language (basis points, not percentages)
Sector rotation analysis
Correlation observations (commodities vs equities)
Technical level identification
Forward-looking bias assessment

Cost Breakdown

I built this for myself, but here's what it would cost at scale:

Service	Monthly Cost	Notes
Lambda	$0.00	Within free tier (400K GB-seconds)
DynamoDB	$0.09	137 MB storage + 165K operations
Bedrock	$0.14	60 analysis runs/month
SES	$0.20	3,000 emails (first 1K free)
S3	$0.01	25 MB storage
CloudFront	$0.00	Within free tier (1 TB)
CloudWatch	$0.06	Logs and monitoring
TOTAL	$0.50	$0.005 per user

Scaling Economics

1,000 users: $2.50/month ($0.0025/user)
10,000 users: $20/month ($0.002/user)

Key insight: Most costs are fixed (data processing). Only email scales linearly.

Lessons Learned

1. Serverless Isn't Always Cheaper

For always-on, high-traffic applications, EC2 can be cheaper. But for scheduled jobs (cron-like), bursty traffic, and low-medium volume APIs, serverless wins on both cost and simplicity.

2. DynamoDB Requires Different Thinking

Coming from SQL: No JOINs (denormalize data), design for access patterns not normalization, use composite keys (ticker + date), leverage GSIs sparingly.

But once you adapt: Blazing fast queries, no connection limits, predictable performance.

3. AI Prompt Engineering > Model Selection

I spent more time refining prompts than choosing models. Claude 3 Haiku (cheapest) produces better results with a good prompt than GPT-4 with a mediocre one.

Prompt iteration:

v1: Generic "analyze the market" → vague output
v2: Structured sections → better but robotic
v3: Data-only constraint → accurate but dry
v4: Institutional voice → professional but verbose
v5: Flowing prose + precise metrics → perfect

4. Cache Aggressively

Added 2-hour TTL cache in DynamoDB:

Reduced Lambda invocations by 80%
Improved API response time (50ms vs 2s)
Cost: $0.01/month

5. EventBridge > Cron

EventBridge advantages: Visual workflow in AWS Console, built-in retry logic, dead letter queues, CloudWatch integration, no server to run cron on.

Performance Metrics

Latency

Data fetch: 60s (214 tickers from Yahoo Finance)
Feature calculation: 30s (124 tickers, 20+ indicators)
AI analysis: 3s (Claude 3 Haiku)
Email delivery: 2s per email
API response: 50ms (cached), 2s (uncached)

Reliability

Uptime: 99.9% (AWS SLA)
Failed Lambda invocations: <0.1%
Email delivery rate: 99.5%

Conclusion

Building a professional-grade market intelligence platform doesn't require expensive servers, complex Kubernetes clusters, dedicated DevOps teams, or $10K/month infrastructure budgets.

It requires:

Smart architecture choices
Leveraging managed services
Understanding your access patterns
Aggressive caching
Good prompt engineering

Final stats:

214 tickers tracked
13,500+ historical records
20+ technical indicators
Market analysis twice daily
Professional HTML emails
Interactive web interface
$0.50/month (scales to 100 users at this cost)

I built this for my own investing research, but the architecture scales effortlessly. The serverless revolution is real.

Tech Stack Summary

Backend: AWS Lambda (Python 3.11), DynamoDB (NoSQL), EventBridge (Orchestration), Bedrock (AI), SES (Email)

Frontend: S3 (Static hosting), CloudFront (CDN), Vanilla JavaScript (No framework)

Data Sources: Yahoo Finance (Free)

Development Tool: Built with Kiro (AWS AI assistant)

Total Lines of Code: ~2,500
Development Time: 1 weekend
Monthly Cost: $0.50 (my usage, scales to 100 users)

I built this for tracking market trends using Kiro to accelerate development. The economics are remarkable: professional-grade infrastructure for less than a coffee per month.

What's Next: Data Sources

The current system uses Yahoo Finance for price data. Here are additional data sources planned for integration:

Earnings Calendar

Upcoming earnings dates for tracked tickers

Alert system 1-2 days before earnings

Historical earnings surprise data

Post-earnings price movement analysis

Options Flow Data

Unusual options activity detection

Large block trades (whales)

Put/call ratio by ticker

Implied volatility changes

Insider Trading

SEC Form 4 filings (insider buys/sells)

Cluster detection (multiple insiders buying)

Historical correlation with price moves

Short Interest

Days to cover ratio

Short interest % of float

Short squeeze potential scoring

Trend analysis (increasing/decreasing)

Analyst Ratings

Consensus ratings (buy/hold/sell)

Price target aggregation

Upgrade/downgrade alerts

Analyst accuracy tracking

All data sources will be integrated using the same serverless architecture, keeping costs minimal while adding significant analytical depth.