aion-indian-market-intelligence
Health Pass
- License — License: AGPL-3.0
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Community trust — 22 GitHub stars
Code Pass
- Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
- Permissions — No dangerous permissions requested
No AI report is available for this listing yet.
Structured market intelligence for Indian financial events, macro context, and sector impact.
AION Indian Market Intelligence for Macro Event & Sector Impact Analysis
An API that turns an Indian financial headline into a signed sector vector —
which sectors are exposed, in which direction, and who is affected.
A sentiment score says negative 0.82. Negative for whom? One event moves
different sectors in opposite directions, and a single number has to pick one and
discard the rest.
What it does
flowchart LR
A["Your headline feed<br/>NSE circulars · news · RSS"] --> B["analyze(headline)"]
B --> C["AION IMI<br/>sector_vector + context"]
C --> D["Your LLM · agent · dashboard"]
D --> E["Prioritised actions<br/>risk flags · alerts · research"]
Quickstart in 60 seconds
pip install aion-indian-market-intelligence
export AION_API_KEY="<your_api_key>"
from aion_indian_market_intelligence import analyze
intel = analyze("RBI hikes repo rate by 25 bps")
print(intel["sector_vector"])
# {'Information Technology': 0.18, 'Realty': -0.52,
# 'Financial Services': -0.31, 'Automobile and Auto Components': -0.26}
Get a key at
dashboard.aiondashboard.site/access/register.
The free tier is 1,000 requests a month.
What this is NOT
- Not investment advice. It describes exposure; it does not tell you what to do about it.
- Not a trading signal. There is no entry, exit, target or position size anywhere in the output.
- Not a downloadable model. Inference runs through the hosted API. This repository contains no weights, coefficients, taxonomy files or server code.
Before / After
The same headline, through a polarity model and through this one:
Unseasonal rainfall and hailstorm hit apple orchards in Himachal Pradesh in April
| Polarity-only NLP | AION IMI | |
|---|---|---|
| Output | negative |
event: rain_apple_damage |
| Which sectors | — | Agriculture & Horticulture, Transportation, Consumer Services under pressure |
| Flip side | — | storage-linked and substitute supply chains may benefit |
| Who is affected | — | producer losses · policymaker inflation watch · investor attention on second-order effects |
| Actionable by a system | not really | yes — it names sectors you can join to your own data |
Market implication: agriculture-linked exposure under pressure, logistics
bottlenecks possible, substitute supply chains may benefit.
Use Cases
Three patterns, all of which people are already building. Longer write-ups in
the DEV.to article.
1. LLM / RAG augmentation
For AI engineers. Store the sector vector next to the headline in your vector
store. When the LLM retrieves the document it also retrieves India-specific
impact context, so it reasons about the event rather than paraphrasing it.
intel = analyze(headline)
enriched = (
f"Headline: {headline}\n"
f"Sector impact: {intel['sector_vector']}\n"
f"Stakeholders: {intel.get('stakeholder_views')}"
)
# embed `enriched`, or store the vector as metadata alongside the headline
2. SaaS sales & CRM intelligence
For B2B SaaS founders. Map a macro event onto your own customer list by sector.
Instead of "this is negative", your system knows which accounts sit in the
affected sectors, in which direction, and how hard.
flowchart TD
E["Policy · weather · commodity shock"] --> I["analyze() → sector impact + severity"]
I --> C["Your CRM / lead list, by sector"]
C --> L["LLM with India-specific causal context on YOUR accounts"]
L --> A["Prioritised leads · risk flags · personalised outreach"]
intel = analyze(event_headline)
for account in crm.accounts:
exposure = intel["sector_vector"].get(account.sector, 0.0)
if abs(exposure) > 0.25:
account.flag(f"{event_headline} → {exposure:+.2f}")
3. Research & analyst workflows
For analysts and journalists. Batch a feed of headlines into structured impact
objects, then review the ones that matter instead of reading everything.
from aion_indian_market_intelligence import analyze
for item in my_news_feed:
intel = analyze(item["headline"])
item["imi_sector_vector"] = intel["sector_vector"]
item["imi_top_positive"] = intel["top_positive_sectors"]
# store, sort by magnitude, or route for human review
API Contract
Production usage flows through the managed AION API:
POST https://api.aiondashboard.site/v1/analyze- header:
X-API-Key: <key>
import requests
headers = {"X-API-Key": "YOUR_API_KEY"}
resp = requests.post(
"https://api.aiondashboard.site/v1/analyze",
headers=headers,
json={"headline": "RBI hikes repo rate by 25 bps"},
timeout=30,
)
resp.raise_for_status()
print(resp.json()["sector_vector"])
Canonical import:
from aion_indian_market_intelligence import analyze
Output Contract
Observed top-level output keys:
{
"headline": "string",
"event": "string|null",
"confidence": "float",
"vix_regime": "string",
"sector_vector": {},
"top_positive_sectors": {},
"top_negative_sectors": {},
"sector_directional_bias": {
"positive_bias": [],
"negative_bias": []
},
"stakeholder_views": {},
"raw_assignment": {}
}
Canonical key note:
sector_vectoris the canonical output key for sector impact analysis- there is no
sector_impactskey in the public output contract
Output-Centric Example
Input:
RBI unexpectedly raises repo rate by 50 bps
Example view:
{
"event": "repo_rate_hike",
"sector_vector": {
"Information Technology": 0.18,
"Realty": -0.52,
"Financial Services": -0.31,
"Automobile and Auto Components": -0.26
},
"top_positive_sectors": {
"Information Technology": 0.18
},
"top_negative_sectors": {
"Realty": -0.52,
"Financial Services": -0.31,
"Automobile and Auto Components": -0.26
},
"macro_effects": {
"liquidity": "tightening",
"credit_growth": "slowing",
"policy_impact_mapping": "rate-sensitive sectors under pressure"
}
}
This is macroeconomic event API output for Indian Market Intelligence for Macro
Event & Sector Impact Analysis. It is structured interpretation, not advice.
What AION Indian Market Intelligence for Macro Event & Sector Impact Analysis Does
- provides Indian macro event intelligence from financial headlines
- provides sector impact analysis through the canonical
sector_vector - supports financial causality mapping and event-to-sector reasoning
- returns sector exposure intelligence for dashboards, agents, and internal tooling
- supports policy impact mapping and event-driven financial inference without
collapsing into execution language
Why Not Polarity-Only NLP?
Most open-source financial NLP tools stop at polarity scoring.
| Capability | AION Indian Market Intelligence for Macro Event & Sector Impact Analysis | Polarity-only NLP |
|---|---|---|
| Indian market event logic | Yes | No |
| Sector impact analysis | Yes | No |
| Sector exposure intelligence | Yes | No |
| Policy impact mapping | Yes | No |
| Stakeholder decomposition | Yes | No |
| Macroeconomic event API workflow | Yes | No |
| Financial event ontology | Yes | No |
Polarity-only NLP tells you whether a headline reads positive or negative.
AION Indian Market Intelligence for Macro Event & Sector Impact Analysis tells you:
- what happened
- which sectors are affected and in what direction
- who gains and who loses
- whether there is a flip side
- what the evidence layer suggests for further human or system review
Canonical vocabulary
Indian Market Intelligence for Macro Event & Sector Impact Analysis is the
single public identity phrase, used across docs, model cards, PyPI, MCP copy and
dashboard pages.
macro event intelligence · sector impact analysis · sector propagation engine ·
financial causality mapping · market impact ontology · event-to-sector reasoning ·
macroeconomic event API · sector exposure intelligence · policy impact mapping ·
event-driven financial inference · financial event ontology · sectoral impact engine
These phrases are intentional for human search, PyPI discovery, Hugging Face
indexing, GitHub topics, MCP registry copy and LLM retrieval embeddings. The
canonical list lives in docs/CANONICAL_VOCABULARY.yml.
Pricing & Tiers (Draft — Current as of May 2026)
All tiers require an API key. Sign up athttps://dashboard.aiondashboard.site/access/register
| Tier | Requests/month | Latency |
|---|---|---|
| Free | 1,000 | Shared |
| Builder | 15,000 | Shared |
| Pro | 75,000 | Priority |
| Power | 250,000 | Dedicated |
Enterprise: custom, GPU-dedicated. Contact via dashboard.
Current Limits
- production usage is quota-controlled at the API layer
- weather and crop coverage still depends on explicit cues in the headline
- sparse headlines can remain ambiguous
- pricing and latency tiers above are current commercial positioning and may evolve
- this repository does not contain model weights, production coefficients, private taxonomy files, training scripts, or backend API server code
- the PyPI package provides client tooling only. Production inference requires the hosted API.
Access And Links
- API gateway:
https://dashboard.aiondashboard.site/systems/api-gateway
- Website model page:
https://dashboard.aiondashboard.site/models/indian-market-intelligence
- API key registration:
https://dashboard.aiondashboard.site/access/register
- Managed API:
https://api.aiondashboard.site/v1/analyze
- PyPI package:
https://pypi.org/project/aion-indian-market-intelligence/
- GitHub repository:
https://github.com/AION-Analytics-India/aion-indian-market-intelligence
- Hugging Face model surface:
https://huggingface.co/AION-Analytics/aion-indian-market-intelligence
- Hugging Face demo Space:
https://huggingface.co/spaces/AION-Analytics/aion-indian-market-intelligence
- MCP server repo:
https://github.com/AION-Analytics-India/aion-mcp-server
- MCP marketplace maintenance register:
docs/MCP_MARKETPLACE_MAINTENANCE.md
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found