AION Indian Market Intelligence
Structured macro intelligence for real-world events. You supply the event text — an RBI circular, a budget announcement, a cyclone warning, a geopolitical headline — and IMI returns which Indian sectors are affected, in which direction, over what time horizon, with the causal reasoning and a confidence attached.
AION Analytics (India) — distinct from Polymathic's AION (astronomy), Aion Analytics LLC (United States), and aion-labs (Israel).
Deployed model Signed sector vector Lagged impact (lag 0 / lag 90) Five stakeholder views MCP-compatible Proprietary — hosted API
What it actually does
You send one piece of event text — a headline, circular, notification, or manual note — and IMI returns structured, explainable intelligence: the classified event, macro context, a signed and time-lagged sector-impact vector, commodity and stakeholder impact, a confidence score, and the evidence behind the result. Structured intelligence with an auditable result — not a black box, not keyword sentiment, not a data pipe.
The sector vector is signed and time-lagged. The same sector can carry a negative score at lag 0 and a positive score at lag 90 — as happens in construction after a cyclone (immediate damage, then rebuilding allocation). A keyword sentiment tool cannot produce this. A market data pipe does not produce this.
Receipt 1 — Monetary policy hold
Input headline submitted on 5 Jun 2026 (RBI MPC decision day).
{
"headline": "RBI MPC holds repo rate at 6.50% — June 2026 decision",
"event": "monetary_policy",
"event_subtype": "repo_rate_hold",
"confidence": 0.91,
"vix_regime": "normal",
"sector_vector": {
"Banking & Financial Services": 0.38,
"NBFCs": 0.14,
"Real Estate": -0.44,
"IT Services": -0.21,
"FMCG": 0.09
},
"stakeholder_views": {
"depositors": "neutral — FD yields stable, no compression from cut",
"home_loan_borrowers": "relief — EMI burden unchanged, floating rate stable",
"banks": "positive — CASA margins intact, NIM pressure absent",
"equity_investors_financials":"positive — outperform expected vs broader index",
"equity_investors_it": "negative — dollar-sector headwinds, global risk-off"
}
}
Actual session result that day: Nifty Bank +0.35%, Fin Services +0.10% vs Nifty 50 −0.21% and IT −0.99%. The model called Banking and Financials positive; both outperformed the index by 0.56 and 0.31 percentage points respectively. Correct directional alpha for every named sector.
Not investment advice. The model describes causal structure; execution decisions remain with you.
Receipt 2 — Bidirectional, time-lagged, five stakeholder views
This is the case that distinguishes causal structure from sentiment. Same sector, opposite signs, 90 days apart.
{
"headline": "Severe cyclone makes coastal landfall, widespread damage to AP coastal districts",
"event": "weather_disaster",
"event_subtype": "cyclone_coastal",
"confidence": 0.84,
"vix_regime": "elevated",
"sector_vector": {
"Construction": { "lag_0": -0.50, "lag_90": 0.55 },
"Agriculture": { "lag_0": -0.65, "lag_90": -0.65 },
"Power": { "lag_0": -0.38, "lag_90": -0.12 },
"Financials": { "lag_0": -0.29, "lag_90": -0.18 },
"FMCG": { "lag_0": -0.22, "lag_90": 0.05 }
},
"stakeholder_views": {
"government": "Construction opportunity at 90d — rebuilding allocation, fiscal expansion expected",
"agricultural_producers": "Agriculture net negative — crop damage, recovery slow regardless of lag",
"insurers": "Claims pressure; coastal exposure repricing likely",
"logistics_operators": "Near-term disruption; medium-term normalization once ports reopen",
"equity_investors": "Construction net positive at 90d; Agriculture and Power net negative"
}
}
Developer use-cases
SaaS and fintech builders
Add an event-aware sector-impact layer to Indian market dashboards. When a RBI decision, budget announcement, or commodity shock lands, your dashboard surfaces structured causal context — not just a headline. One API call; structured JSON sector vector ready for downstream rendering.
Risk and exposure mapping
Map sector exposure per event before an analyst reviews it. The signed sector vector with lag offsets lets risk systems flag positions in Agriculture before a monsoon signal arrives, or flag Construction exposure changes over two different horizons from the same cyclone event.
LLM and agent builders — the MCP tool
Connect Claude, GPT, or any MCP-compatible agent to Indian market sector-impact context. When an agent parses a news feed, the analyze_news tool returns the sector vector, stakeholder breakdown, VIX regime, and lag structure — so the agent reasons about what the event means, not just what it says.
Fetch Indian market data with any MCP. Understand what it means with this one.
MCP integration
Install and run:
uvx aion-indian-market-intelligence-mcp
Claude Desktop config:
{
"mcpServers": {
"aion-indian-market-intelligence": {
"command": "uvx",
"args": ["aion-indian-market-intelligence-mcp"],
"env": { "AION_API_KEY": "YOUR_API_KEY" }
}
}
}
The analyze_news tool — one input, full sector vector output (see receipts above). Nothing is bundled or run locally in the MCP server; all inference runs on the hosted AION API.
Python SDK:
pip install aion-indian-market-intelligence
from aion_indian_market_intelligence import analyze
result = analyze("RBI MPC holds repo rate at 6.50%")
print(result["sector_vector"])
Product separation
| AION System | Retrieval Domain |
|---|---|
| Indian Market Intelligence | Macro events → signed, time-lagged sector-impact vector across 32 NSE sectors |
| Edge Engine | 5-minute intraday microstructure → tradability scoring |
| Veritas | Pre-open futures tape → NIFTY / BANKNIFTY / SENSEX opening band |
| Sentinel | Corporate filings → Companies Act anomaly detection |