Case study
Ranked Trade Ideas Every Morning for an EU Investment Bank
How SquareShift built a unified data lake and separate FX and equity recommendation engines that generate ranked trade ideas every night for a multinational investment bank.
Book a session →
Client
A multinational investment bank headquartered in the EU, serving institutional clients across Europe and North America.
Industry
Financial Services
Services
Stack
DTW Clustering · Cross-Correlation Analysis · PageRank · RFM Model · Tableau
How SquareShift delivered it.
The challenge
The client's sales and trading desk handled a large volume of transactions but had no systematic way to see which FX and equity trades were worth recommending. Transactions, meeting notes, and investment goals lived apart from each other.
What we delivered
SquareShift built a data lake that unified transactions, meeting notes, and investment goals in one place. On top of it, the team built a separate FX recommendation engine using DTW clustering, cross-correlation analysis, and PageRank, and a separate equity recommendation engine built on the RFM model.
The outcome
Both engines generate ranked trade ideas every night. Bankers now open ranked FX and equity trade recommendations every morning in Tableau instead of building them from scratch.
A recommendation engine only earns a banker's trust once it replaces a blank research queue with a ranked list they can act on before their first coffee.
AI & Machine Learning Practice Lead, SquareShift
Related reading: risk signal detection with OCR and machine learning and wheel defect forecasting with machine learning.
