NIFTY-50 · CORRELATION GRAPH · KNN K=4 · LOUVAINCOMPUTING…
COMPUTING GRAPH…
WINDOW60 BARS
Move the dial to measure displacement

The market
is not a list.

We rebuild the NIFTY-50 correlation graph from 1-minute bars and measure where every stock sits inside it. Move the window dial above: between a 30-bar and a 120-bar estimate, 75% of the edges change and the most-central stock is a different name entirely. The nodes that barely move are the ones you can believe.

Universe
NIFTY 50
tradable names · NSE
Communities
Louvain ·
Modularity
Most central
computing…
The instruments

Not a report. A machine you run.

Every number on this page came out of the same engine you get access to. Set your own window, universe, and metrics — then look.

How it works

Prices in. Structure out.

Most signals stop at the stock. Ours start at the edges between them — and no step is a black box.

01

Log returns, session-aligned

Every stock's OHLCV is resampled from 1-minute bars to your interval, then converted to log returns over a trailing window you choose. The window is the single most consequential parameter in the whole pipeline, which is why we let you move it and watch what happens.

Intervals1m · 5m · 15m · 1h · 1d
02

Correlation becomes structure

Pearson (or Spearman) correlation across the window gives a dense matrix. We sparsify it into a graph — a Mantegna minimum spanning tree by default, or kNN, threshold, or complete. The sparsifier is a choice, and it is yours.

MethodsMST · kNN · θ · complete
03

Where each stock sits

Louvain finds the communities; five centrality measures score each stock's position — eigenvector, PageRank, degree strength, betweenness, closeness. Rebuilt per as-of day, with a fixed seed, so the partition does not shuffle between calls.

Metrics5 per stock
Coverage
NIFTY 50

tradable names on NSE. TMPV is excluded — it has no price history, and we would rather drop a name than fake one.

Granularity
1-minute

Resampled to any interval from 1m to 1d. Nothing is interpolated.

History
2025 →

Rebuilt every session, not backfilled. We have no history before 2025 and we do not claim any.

Specification

One engine. Two access levels.

The ladder is the engine's own limits — intervals, sparsifiers, window depth, run count. Paid unlocks the wider engine, and a lot more is available on request.

ParameterFreePaid
Price₹0TBD
UniverseNIFTY-50NIFTY-50 · NIFTY-500 · custom †
Intervals1d1m · 5m · 15m · 1h · 1d
Graph methodsMST · kNNMST · kNN · threshold · complete · more †
CorrelationPearson · SpearmanPearson · Spearman · more †
Centrality metricsAll 55 + more †
Max lookback100 bars300 bars · deeper †
As-of days per run1010 · more †
Symbols per run5050 · more †
Runs5Unlimited
CSV exportYesYes
Network graphYesYes
† Paid — available on requestWe run more than the toggles above expose. Tell us what you need and we'll set it up.
  • Wider universes — NIFTY-500 and custom baskets of your own symbols
  • More instruments and longer price history
  • Additional centrality metrics beyond the core five
  • Further graph constructions and sparsifiers
  • More correlation estimators (distance, partial, tail-dependence, …)
  • Deeper lookback windows and longer rolling series
  • Full intraday at scale, and bespoke research runs

Skylife Research provides quantitative research and data, not investment advice. Graph centrality measures market structure — it is a research input, not an entry or exit signal. Trading involves risk.

FAQ

Skeptical? Good.

The questions a serious desk asks before it trusts anyone's numbers.

What universe and history do you cover?

The NIFTY-50 — 49 tradable names — on NSE. Underlying data is 1-minute bars from January 2025, resampled to whatever interval you ask for. There is no history before 2025 and we don't claim any.

Why does the graph change so much when I move the window?

Because correlation is estimated, not observed. Between a 30-bar and a 120-bar window, 75% of the edges in this graph change and the most-central stock goes from JIOFIN to BAJAJFINSV. That instability is not a bug in our pipeline — it is a property of the data, and most vendors simply pick one window and never show you the others.

Is this a signal I can trade directly?

No — and we'd rather say so. Graph Stats measures market structure: who is central, who is peripheral, and how that shifts. It's a research input, not an entry/exit signal. Anyone selling you centrality as alpha is skipping several steps.

Do you model lead-lag — who moves before whom?

No, and we won't. We tested it: of 2,450 directed pairs, zero survive a 10% false-discovery-rate null. So there is no lead-lag product, and nothing on this site animates a directed flow between two stocks, because that would imply a relationship our own research rejects.

Can I run it on my own symbols?

Yes. Pass any comma-separated symbol list instead of the default universe, up to 50 names, and the whole pipeline runs on that set.

Why Louvain, and is the clustering stable?

Louvain is fast enough to rebuild the graph per as-of day, which is what makes the time series possible. We run it with a fixed seed, so the same window always yields the same partition. Modularity is reported with every result so you can judge how real the separation is.

How fresh is the data?

The graph is rebuilt from the database on each run. A full-universe query takes roughly 10–15 seconds because it genuinely recomputes every graph in your window rather than serving a cached picture.

What happens if the engine is down?

The page says so. It will not fall back to invented placeholder numbers dressed up as today's market — an earlier version of this site did exactly that, and it was wrong.

Is there an API?

Yes. Sign in with Google, open Dashboard → API access, and generate a 24-hour Bearer token. The full reference, with a live “Try It”, lives at developers.skyliferesearch.com. Every metric the Graph Stats tool shows is available as raw JSON.

What are the API rate limits?

On the free developer tier: 1 request per minute and 30 requests per day, per account. Every response carries X-RateLimit-* headers so you can pace yourself. Need more throughput? That's one of the things we lift on request.

Can I get more than the NIFTY-50 — NIFTY-500, my own symbols, more history?

Yes, on request. We already run wider universes (NIFTY-500 and custom baskets), more instruments, longer history, additional metrics, further graph methods, and more correlation estimators — they're simply gated behind a conversation rather than a self-serve toggle. Tell us what you need.

What does Paid cost?

It's TBD, and we won't invent a number to fill the cell. Paid unlocks the full engine — all intervals, all sparsifiers, deeper windows, unlimited runs — plus anything on the on-request list. Contact us and we'll scope it to what you actually need.

How do I get started?

Sign in with Google and open the Graph Stats tool — the free tier runs a real NIFTY-50 daily snapshot, no card required. Prefer code? Generate an API token from the dashboard and hit the endpoint directly.

Is this investment advice?

No. Skylife Research provides quantitative research and data, not advice. Graph centrality measures market structure — it is a research input, not an entry or exit signal, and trading involves risk.

Contact

Ask us anything.

Questions about the methodology, the data, API access, or the paid tier — or a wider universe and features on request. We read and reply to every message.

If you want to evaluate this for a desk, bring one portfolio and a window length you trust. We will run the graph on it live and show you which of your positions are the same bet.

Based
Mumbai, Maharashtra, India