🧭

Time-Series Forecasting

Predicting what comes next when the past is your only guide.

Part 1

Charting a Course With Only the Wake Behind You

why forecasting is fundamentally different from every other prediction problem: you only ever see where you've already been.

Part 2

What the Navigator Is Actually Trying to Do

the real difference between describing a sequence's past and genuinely predicting where it's headed next.

Part 3

Dead Reckoning

why the simplest possible forecast — tomorrow looks like today — is a surprisingly strong baseline that every real model has to beat.

Part 4

Reading the Current

how to separate a sequence's persistent, long-term direction from its short-term noise — the first step in understanding what's actually moving it.

Part 5

Following the Tides

how recognizing regular, repeating cycles in a time series — the tides — separates predictable rhythm from genuine unpredictability.

Part 6

The Unpredictable Squall

why every forecast has an irreducible amount of genuine randomness left over, and why that's a fact about the world, not a modeling failure.

Part 7

Decomposing the Voyage

how formal decomposition splits a time series into trend, seasonality, and noise as three separate, combinable pieces.

Part 8

Classical Instruments

how ARIMA models a time series' own past values and past errors to produce a rigorous, well-understood forecast.

Part 9

Watching the Compass Drift

how exponential smoothing weights recent observations more heavily than old ones, adapting gradually as conditions genuinely change.

Part 10

Charting Multiple Routes

why forecasting one sequence in isolation misses information that related sequences can provide, and how multivariate forecasting captures it.

Part 11

The Modern Fleet

how gradient boosting and other machine learning methods reframe forecasting as a standard supervised learning problem with engineered time-based features.

Part 12

Deep Water Navigation

how LSTMs and transformer-based models handle long, complex sequences and multiple related series in ways classical methods can't.

Part 13

How Far Can You See

why forecast accuracy degrades predictably the further into the future you look, and why the honest answer to 'how far ahead can we forecast' is 'it depends on the horizon.'

Part 14

The Confidence Interval Is the Storm Radius

why a single point forecast without an honest uncertainty range is dangerously incomplete, and how prediction intervals fix that.

Part 15

When the Map Redraws Itself

why a forecasting model trained on historical patterns can quietly stop working once the underlying dynamics genuinely change.

Part 16

Choosing the Right Instrument

how backtesting lets you rigorously compare forecasting methods on real historical data before trusting any of them with a real decision.

Part 17

The Navigator's Logbook

how metrics like MAPE and RMSE turn 'how good was this forecast' into a precise, comparable number, and why the choice of metric genuinely matters.

Part 18

Forecasting as a Team Sport

why combining forecasts from several different methods often beats relying on any single one, however well it backtested.

Part 19

When Everyone Reads the Same Chart

how hierarchical and large-scale forecasting keep thousands of related predictions coherent with each other, not just individually accurate.

Part 20

Landfall

reassembling the whole voyage, from a wake trailing behind an uncertain ship to a coordinated fleet of forecasts reaching landfall together.