Market prediction platform
A financial analysis firm read the same charts every day and hand-labelled every trend and oscillator. We turned that method into a machine-learning platform — models that make the readings, a daily pipeline that fills in their spreadsheet, and predictions served through an API to build on.
One analyst's eye, scaled. Our client analyses financial markets with a detailed personal system — trend patterns, moving averages and a set of oscillators, each read off a chart and marked with a direction. Doing it by eye was slow, repetitive and impossible to scale. We turned the method into supervised machine-learning models, then built the platform around them: a daily time-series pipeline, per-indicator accuracy checks and an API serving predictions — with an eye throughout on keeping the compute affordable at scale.
What we built
-
Trend and oscillator models
Supervised models trained on the analyst's own labelled history to read price action, moving averages and each oscillator the way they would by eye.
-
Daily time-series pipeline
A pipeline that pulls each day's price and indicator data, runs the models and writes the labels back into the client's working spreadsheet — no manual copying.
-
Per-indicator accuracy checks
The model's labels measured against the analyst's own, indicator by indicator, so accuracy is proven before it's relied on.
-
Prediction API
Predictions served through a clean API, so the client can build their own products on top without touching the models underneath.
Why this matters to you:
The daily read-and-label routine now runs itself, consistently, and the same models serve predictions as a service the client can build products on — expert judgement, scaled past what one analyst could ever watch.
Keep exploring
-
Wealth planning, made simple. BonsaiCodeLeap is the development team behind Bonsai, a UK wealth app. We build and ship the mobile product across Android and iOS — planning tools, bank connections and premium tiers — releasing new features every sprint.
read more -
SBUCodeLeap automated the full sales cycle for a client in the UK energy sector, from lead capture through to signed contract, increasing lead generation capacity by 5x in 3 months.
read more -
WeSnagA large London-based construction company managing major residential sites — dozens of contractors, thousands of defects — came to CodeLeap for a digital snagging platform. Within 6 months, we delivered a fully functioning mobile app that reduced human errors and accelerated the snagging process for construction managers.
read more
