Recommendation System

Recommendation System

Informational Filtering System That Predicts

Recommendation System

A recommended system is an informational filtering system that predicts a rating that a user would give to an item or a service. It is based both on the characteristics of the user and the characteristics of the item/service. These systems are seeing widespread use especially among large online retailers and content providers as they can leverage existing consumer data to generate deeper insights about the likes and dislikes of their audiences.


Amazon – uses recommendations as a targeted marketing tool in both its email campaigns and its web site pages. According to McKinsey, 35% of Amazon’s revenue is generated by its recommendation engine.

YouTube – leverages Google Brain as a tool to provide video recommendations. It provides users with a truly personalised feed and allows more than 70% of the time people spend watching videos is driven by YouTube’s algorithmic recommendations.

Netflix ­– splits its viewer base into over 2000 different taste groups and uses both explicit (giving a thumbs up to the video) and implicit data (binge watching a series over 2 days) to dictate which recommendations are sent.

How it can be applied to finance

The corporate clients of multinational banks are often sent thousands of recommendations of different instruments each month. These are generally done in bulk without a recommendation engine. Reducing the number of recommendations can improve the relationship between the bank and its client.


Policies and strict governance can prevent rogue trading but another more direct way is stricter controls on the technologies used for booking these trades. Inefficiencies and inconsistencies in databases used within banks may allow traders to hide these trades from the central risk book. DataSpartan worked on a Blockchain proof of concept platform that addressed these database inconsistencies.


A Blockchain type solution allows different departments within the bank to have a consistent view of orders – this is because it is impossible to delete or change any of the executed trade orders without other departments agreeing. This provides transparency about trade execution and minimises the chance of rogue trading.


The proof of concept is now being fully integrated into a subset of the servers in the multinational bank for live testing. APIs have also been built to allow developers to interface with Blockchain functions.