Private Markets Screening & Filing Intelligence
The system narrows a company universe with deterministic financial rules, then links the resulting screen to the filings and passages an analyst should review.
Central findingThe current system links 280 companies with SEC fundamentals and retrieves relevant evidence from 15,965 filing chunks, while keeping scoring rules and source passages inspectable.
Evidence
The result in context
- Companies screened
- 283
- Companies with SEC fundamentals
- 280
- Filing chunks
- 15,965
- Precision@5
- 89.4%
- Relevant evidence among the top five retrieved passages.
Question
Can financial screening and filing retrieval reduce repetitive work without hiding the evidence or replacing analyst judgement?
A transparent screening and filing-retrieval workflow combining company fundamentals, SEC evidence and local search.
Workflow
From a broad universe to reviewable evidence
A deterministic scorecard filters companies using financial fundamentals. SEC XBRL data supplies structured evidence; filing retrieval then surfaces relevant passages for analyst review.
The system is intentionally not a black-box recommendation engine. Scores, source filings and retrieved text remain inspectable.
Research workflow
From universe to reviewable evidence
Automation narrows and retrieves; an analyst still owns the decision.
- 01Universe
288 attempted · 283 successfully screened.
- 02Financial screen
Transparent rules narrow the set without hiding exclusions.
- 03SEC fundamentals
280 companies connect to structured public fundamentals.
- 04Filings
35 filings supply primary-source context.
- 05Evidence retrieval
15,965 chunks make passages searchable and testable.
- 06Analyst review
The workflow ends with judgement, not automatic recommendation.
Interactive evidence
Valuation and growth are reviewed together, not collapsed into one rank
256 public-company observations with complete EV / sales and year-on-year revenue-growth fields.
Read: The screening score directs attention; the scatter preserves sector, valuation and growth context before any company is promoted for review.
Data table · 256 verified rows
| Ticker | Company Name | Sector Theme | Ev To Sales | Revenue Growth Pct | Market Cap | Investment Screening Score |
|---|---|---|---|---|---|---|
| AMP | Ameriprise Financial, Inc. | Alternative Asset Managers / Market Infrastructure | 1.842192 | 5.494812 | 39,526,850,560 | 60.3 |
| BEN | Franklin Resources, Inc. | Alternative Asset Managers / Market Infrastructure | 2.25835 | 3.452465 | 16,293,222,400 | 60 |
| MCO | Moody'S Corporation | Business Services | 11.002707 | 8.888262 | 79,273,402,368 | 44.6 |
| SBUX | Starbucks Corporation | Consumer Services | 3.740251 | 2.786915 | 115,616,866,304 | 39 |
| ARRY | Array Technologies, Inc. | Energy Transition | 1.895291 | 40.21961 | 1,429,816,192 | 54.3 |
| HCA | HCA Healthcare, Inc. | Healthcare Services | 1.839953 | 7.077603 | 85,968,453,632 | 37.7 |
| ROK | Rockwell Automation, Inc. | Industrials | 6.525392 | 0.94141 | 50,827,714,560 | 46.1 |
| AFRM | Affirm Holdings, Inc. | Payments / Financial Services | 27.749504 | 34.861406 | 24,316,985,344 | 60 |
| KIM | Kimco Realty Corporation | Real Estate / REITs | 11.571956 | 5.061428 | 16,438,250,496 | 63.2 |
| NET | Cloudflare, Inc. | Software / Saa S | 33.816879 | 29.845666 | 79,696,035,840 | 44.8 |
| SEAT | Vivid Seats Inc. | Travel / Leisure / Consumer Platforms | 0.773865 | -30.46531 | 94,381,864 | 34.5 |
| UBER | Uber Technologies, Inc. | Travel / Leisure / Consumer Platforms | 2.909951 | 18.279594 | 142,726,021,120 | 47 |
Retrieval
Evaluation is attached to the research workflow
Across a deterministic 96-question gold set evaluated against cached sample filing chunks, the current benchmark reaches 100% Hit@5, 89.4% Precision@5 and 100% mean reciprocal rank.
Hit@5 asks whether at least one relevant passage appears in the first five results; Precision@5 asks how many of those five are relevant.
Interactive evidence
Retrieval evaluation is attached to the research workflow
Selected committed evaluation metrics across 96 questions.
Read: Hit rate is 100% at three and five results; Precision@5 is 89.44%, keeping the quality trade-off visible.
Data table · 6 verified rows
| Metric | Metric Type | Value Pct |
|---|---|---|
| Hit Rate At 3 | Retrieval | 100 |
| Hit Rate At 5 | Retrieval | 100 |
| Precision At 3 | Retrieval | 98.148148 |
| Precision At 5 | Retrieval | 89.444444 |
| Citation Coverage | Groundedness | 100 |
| No Answer Accuracy | Groundedness | 100 |
Interactive evidence
Risk flags remain separate from the opportunity score
Mean score across all 283 screened companies.
Read: Data-gap risk is lowest on average; drawdown, red-flag and volatility measures cluster around 50 and remain review prompts rather than verdicts.
Data table · 5 verified rows
| Label | Value |
|---|---|
| Credit Risk | 43.284452 |
| Red Flags | 50.032155 |
| Drawdown Risk | 50.176678 |
| Volatility Risk | 50 |
| Data-Gap Risk | 27.396631 |
Status
In development, with boundaries kept visible
The system currently supports structured screening, filing ingestion and local retrieval. Optional local generation remains downstream of source retrieval and human review.
Limitations
What this evidence does not establish
- The retrieval metrics describe a bounded evaluation set and should not be generalised to every filing or analyst question.
- The benchmark uses cached sample filing chunks and is not evidence of legal accuracy, exhaustive diligence or complete real-filing coverage.
- A screen prioritises attention; it does not replace diligence, valuation judgement or primary-source review.
Source and reproducibility
Trace the evidence
Source code, evaluation outputs and supporting material are available in the repository.
View repository- Valuation versus growthdata/processed/investment_scores.csvCommit / evidence ID: 164ad28bd806ccdc182bef3886d4a6e8a9ac4193
- Retrieval evaluationdata/processed/rag_eval_results.csvCommit / evidence ID: 164ad28bd806ccdc182bef3886d4a6e8a9ac4193