MARKET INTELLIGENCE
Generally availableTurn financial news into structured event signals, not bullish/bearish scores.
Earnings, guidance changes, corporate actions, and credit events across 8 languages - including Chinese, Japanese, Hindi, and Korean. Every signal pinned to a config ID your compliance team can replay.
200 labels · 8 languages · p95 target <500ms · Every result reproducible
Event extraction - no sentiment, no opinion
What this analyzer does and doesn't do
- Extract market-relevant event signals from financial text
- Cover 8 languages including Chinese, Japanese, Hindi, and Korean
- Return typed, confidence-ranked events for downstream pipelines
- ✕Predict prices or produce trading signals
- ✕Score sentiment as bullish or bearish
- ✕Provide investment advice or suitability judgments
- ✕Access market data feeds you don’t supply
Sentiqra returns structured signals. Your policy, reviewers, and models make the decision. See the full boundary statement →
WHAT YOU'LL DETECT
Events, not vibes.
Sentiment classifier
{ "sentiment": "negative", "score": 0.72 }
Sentiqra Market Intelligence
{ "code": "guidance_lowered", "level": "label", "score": 0.9, "confidence": "very_high" }
Guidance & Outlook
guidance_lowered
“The company lowered full-year revenue guidance” → very high
Earnings & Financial Results
earnings_miss
“EPS came in well below consensus” → very high
Credit & Liquidity Distress
credit_outlook_worsened
“The rating agency revised the outlook to negative” → high
Mergers & Acquisitions
acquisition_announced
Detected - example withheld
Legal & Investigations
regulatory_investigation_opened
Detected - example withheld
85.4% – 93.2% Production Top-3 Hit Rate across 8 languages.
Benchmarks vary by language - the range above is the honest spread, not the best case. Top-3 Hit Rate means the expected label appears among the 3 highest-confidence signals returned; it measures ranking quality, not whether a thresholded accept/reject decision was right.
WHERE IT GETS USED
Three jobs this analyzer does well.
Systematic quant pipelines
A research desk consumes typed events - guidance revisions, earnings surprises, credit actions - as features in a systematic pipeline. Because detection is deterministic and config-pinned, a backtest replays against the exact analyzer behavior that generated the live signals.
Fit signals: event-driven strategies · backtest integrity · structured features
Compliance and market surveillance
A surveillance team screens announcements and internal communications for market-relevant events under MAR obligations. Every flagged item stores its config ID and signature - a regulator asking "why was this flagged" gets a reproducible answer, not a shrug.
Fit signals: MAR/MiFID exposure · audit obligations · evidence-grade alerts
Multilingual macro monitoring
A treasury team watches central-bank statements and policy releases in Chinese, Japanese, Hindi, and Korean with the same event taxonomy as English coverage - one signal schema across the whole macro feed, no per-language toolchain.
Fit signals: APAC coverage · central-bank watching · unified taxonomy
Send an announcement. Get typed events + a receipt.
POST /v1/analyze
Authorization: Bearer sq_live_your_api_key_here
{
"text": "The company lowered full-year revenue guidance and announced a restructuring of its European operations.",
"language": "en",
"analyzers": ["finance"]
}{
"language": "en",
"signals": [
{ "analyzer": "finance", "code": "corporate_events", "label": "Corporate Events", "score": 0.9, "confidence": "very_high", "level": "category" },
{ "analyzer": "finance", "code": "merger_acquisition", "label": "Merger & Acquisition", "score": 0.9, "confidence": "very_high", "level": "label", "parent": "corporate_events" }
],
"meta": { "analyzers": [{ "name": "finance", "status": "completed", "signal_count": 2, "billed": true }], "partial": false },
"usage": { "analyzer_runs": 1, "billed": true },
"verification": {
"configuration": "sqcfg_TQ2ER9EK",
"fingerprint": "fp_8a72...19f",
"input_commitment": "ic_31bd...a42",
"signature": "sig_ed25519_4c1f...e2a"
}
}READING THE OUTPUT
What a Market Intelligence result tells you - and what it doesn't.
Intended task
Classify market-relevant text - headlines, filings prose, desk notes - into documented event groups like earnings, guidance, M&A, and distress.
Input requirements
text- the only field analyzed; up to 4,096 Unicode code points. Over the limit is rejected withinput_too_long, never truncated.language- must be a language this analyzer supports. Unsupported codes are rejected with400 unsupported_language, never analyzed as a different language.analyzers- include"finance"; up to 2 analyzers per request, one billed run each.- No context beyond
text- no user IDs, history, profiles, or attachments are read or inferred. - Reads one text at a time - no position data, portfolio context, or market feeds are inputs.
Ordinary positive
“Acme raised full-year revenue guidance after Q3 results beat consensus; the board also authorized a buyback.”
Safe inference: The text describes earnings, guidance, and capital-return events. Route it to the sectors and instruments your coverage maps to.
Confusing negative · Insufficient context
“Traders speculated that Acme might raise guidance when it reports next quarter.”
What happens: Event-group signals can fire on speculation: the text describes a possible guidance event in the documented vocabulary. A signal marks what the text is about - not that the event is confirmed.
Why it's tricky: Rumors, previews, and post-event coverage share vocabulary with confirmed announcements. The Information Quality & Social Signals group exists partly for this distinction, but no signal confirms that a described event actually happened or that figures are accurate.
What you can safely infer
- Which documented event types the text describes, and at what signal-match strength.
- That results are reproducible - the same filing text on the same pinned configuration always classifies the same way.
What you must not infer
- ✕That a described event is confirmed, accurate, or material.
- ✕A price or trading recommendation - signals classify text, they do not predict markets.
- ✕That unflagged text is market-irrelevant - a missing signal is "not detected," never "ignore."
Boundary: Signals describe the language of a text, not market facts. Market Intelligence is not investment advice and does not verify that a reported event occurred.
Market Intelligence is on every plan. Even Free.
Free
5,000 runs/mo
Build
$149/mo · 50,000 runs/mo
Growth
$349/mo · 150,000 runs/mo
Production
$799/mo · 500,000 runs/mo
Scale
$2,999/mo · 2,500,000 runs/mo
Enterprise
By agreement · SOC 2 Type II in progress
Deterministic by construction, provable by receipt.
A signed verification receipt - configuration ID (sqcfg_...), result fingerprint (fp2_...), input commitment (ic3_...), and Ed25519 signature (sig_ed25519_...) - ships with every successful analysis result. Pin it to the stored decision and a later replay under the same supported configuration and output profile yields the identical canonical result - the difference between "the model said so" and evidence.
Where it fits in your pipeline
Often paired with: Crisis Intelligence for geopolitical market drivers, Disinformation for coordinated market narratives, Emotion Analysis for communications tone.
Used in: Market Intelligence
Run last quarter's earnings call through it.
5,000 analyzer runs/month · No card required
Analyzer FAQ
New to Sentiqra? It's a deterministic text-analysis API - you send text, you get labeled, confidence-scored signals plus a replayable receipt. Market Intelligence is the market-moving event detection analyzer.
What does Market Intelligence detect?
Detect market-moving events, corporate actions, credit risk, macroeconomic signals, and financial incidents.
Which languages does it cover?
8 supported languages, each with a published per-language benchmark. Coverage is per-analyzer, not platform-wide - check the language list on this page before assuming parity with other analyzers.
How do I call it?
POST /v1/analyze with "analyzers": ["finance"]. Same endpoint, auth, and response shape as every other analyzer - you can pair it with one more analyzer in the same request.
What does a call cost?
One analyzer run per call, billed against your plan's included runs (overage per plan). All GA analyzers are on every plan, including Free - see pricing.
How do I evaluate it on my data?
Label a few hundred of your own examples, run them through the free tier, and compare our signals to your labels. The evaluation playbook walks through building that test set - it's the same method we use internally.