The Daily Finance Brief
The Problem
Every day, useful trade ideas are buried inside my Twitter timeline: scattered across dozens of accounts, diluted by noise, and surfaced by an algorithm that optimizes for engagement, not alpha.
Manual browsing takes hours and still misses things. The signal is there; the infrastructure to extract it isn't.
So I built a project to give me a Daily Briefing.
What lands in my inbox each morning
High Conviction Ideas
Sector Themes
Watchlist
How It Works
Starting from 15 accounts I've traded from, the system maps their social graph to discover new sources worth tracking. The network grows continuously as new connections surface.
Discover
Map the social graph of seed accounts to find new sources
15 seeds → 45+ tracked, growing continuouslyCollect
Pull tweets from all tracked accounts, only fetching new content
~90% reduction in API calls on daily runsExtract
Two-pass LLM: quick filter, then structured data for tickers, direction, and conviction
6,080 tweets → 1,956 actionable callsScore
Check each call against actual market performance at 30, 60, and 90 days
Bayesian composite builds source credibility over timeDeliver
Email a morning briefing with the highest-conviction ideas, sector themes, and watchlist
Daily via Resend, before market openNetwork Discovery
Decisions That Shaped the Project
Local LLM → API
Started with a free local model to avoid cost. But with 6,000+ tweets, 'free' meant a full day of runtime. Switching to gpt-4o-mini cut processing time by 95% for less than a dollar.
Two-Pass Extraction
Most tweets aren't stock calls. A lightweight yes/no classifier runs first. Only the ~30% that pass get the expensive structured extraction.
Why Idea Generation, Not Trading Signals
This tool tells me where to look, not what to buy. The scoring windows (30/60/90 days) are too short for rigorous quant research, and Twitter data isn't reliable enough for automated trading. But as a research filter that surfaces the ideas worth spending time on each morning, it's exactly what I needed.
Does the Scoring Work?
The whole system depends on credibility scoring actually separating signal from noise. Here's what the first run showed:
That spread is the point. The scoring weights ideas from sources with proven track records, so the briefing naturally surfaces better ideas first.
Open Questions
Seed Bias
Network reflects my corner of fintwit. Broader seeding needed to generalize.
Out-of-Sample Validation
Need to split by time period to confirm scoring holds on unseen data.
Risk Adjustment
Measures return, not the drawdown path to get there.