Loading

Data Science_

Fable’s Transaction Data in Action

The Bank of International Settlement (BIS) /The Irving Fisher Committee (IFC) in collaboration with the Bank of Italy has just released its Bulletin on Data Science and Machine Learning in Central Banking. This includes a report on card based payments, and the unique emerging data science opportunities that card data can provide. The study references...

17 November 2022

Data Science

Fable Data is identified as “one of the UK’s most promising tech companies”

Fable Data has been recognised as “one of the UK’s most promising tech companies” following our inclusion in the eighth Tech Nation Upscale initiative. Known for being the growth platform for an exclusive network of high growth UK tech companies and leaders, this programme recognises the success that Fable has enjoyed since launching in 2017...

05 October 2022

Press

Is Food Delivery still cooking or are taste buds changing?

The rise in the use of Food Delivery apps has been well documented with the pandemic serving up a hearty main course for many of the industry’s participants. However, as we have emerged from the depths of lockdowns delivering consistent tailwinds for growth in 2020 and 2021, we ask the questions – how has this...

Market Insights

Where do we go from here for BNPL?

Buy Now Pay Later (BNPL) is the latest reincarnation of consumer borrowing and has quickly dominated the conscience of the consumer, the media, concerned regulators and incumbent mobile/electronic payment platforms and wallets. Here, I briefly trace the origins of consumer debt for context and then bring the narrative forward to a current review of the...

Data Science

Amazon Prime Day sees UK card transactions increase by 12%

Amazon held its annual Prime Day event on the 12/13th July this year. In an environment where online spending has continued to decline from the highs reached in 2020 and 2021 and the current cost-of- living crisis is biting hard, we were curious to know whether this squeeze on incomes might have dulled the consumer...

Market Insights

Anonymized Transaction Data is Essential for Global Economic Health

Fable Data was recognized by the Hedge Fund Industry as the *Best European Alternative Data Supplier 2021. Put simply we are experts at supplying and interpreting anonymized real time banking and credit card data. This strength enables us to have a finger on the pulse of the latest global economic and market insights. And why...

Data Science

The magic behind an optimised consumer spending panel

At Fable Data we have been very busy working to meet the demand for anonymous European spending data. 2019 was a particularly busy year for us as we onboarded numerous data partners from far and wide across Europe to form our inaugural large scale spending panel. Throughout the last 12 months, as the opportunity for...

Data Science

There has never been a better time to monetise anonymised data

Retail banks are being squeezed by the rising costs of digitisation combined with reducing margins from traditional revenue streams. Anonymised datasets present a significant opportunity to create new, high-margin revenue, while driving more informed decisions for business and government, and broad economic and societal benefits. Four years ago, I was a strategy consultant, working with...

03 January 2022

Data Science

Words to Vectors

Manually tagging millions of rows of transactions with their correct merchant group is extremely time consuming and costly, which is why we train models to do this job for us but how does a computer understand text? Enter the world of word embedding, which revolves around representing words as vectors. Table shows ‘petrol’ in two...

Data Science

“Transactional data is the Mount Everest of the alternative data world” Can it be climbed?

This year the dislocation of consumer spending due to Covid-19 has presented numerous technical challenges for users of transactional data. As consumer behaviour changed radically, this triggered a huge increase in interest from investment companies in Fable’s real time spending data in order to monitor economic trends. We saw that cash spending declined by a...

12 October 2020

Data Science

The cutting edge in data ethics

Ethics has been a top priority at Fable Data since day one. Handling consumer data, even anonymised and at an aggregate level, brings with it a significant responsibility. Our Data Science Team actively checks for sensitive features in the data used to develop and support Fable’s products, which includes maintaining a whitelist of acceptable features...

Data Science

Finding the features: Same stores, eCommerce and key value items

Anonymised consumer transactions lack Personal Data but contain information that we can use to create detailed features to better understand the underlying performance of a business. Total sales and transactions are great predictors of total revenue, but there are deeper signals that are better predictors of profit. One of the first questions an investor asks...

10 February 2020

Data Science

Training never stops…

The most important task for our Data Science Team at Fable Data is to accurately determine the merchants and stock market tickers associated with anonymised consumer credit and debit card transaction strings in order to provide sophisticated insights into consumer spending patterns. Great modelling needs a great training set and we have described in a...

28 January 2020

Data Science

The Great Alternative Data Hack

Fable came in third out of twelve teams in the first European Alternative Data Hackathon, organised by DataScrum in collaboration with a number of alternative data providers and hosted at the Microsoft Reactor in Shoreditch. DataScrum is a community of data scientists and data science enthusiasts based in London. They organize events in the alternative...

04 October 2019

Data Science

Known unknowns

A common data science challenge is creating a data set for training models. We discuss tagging and generating synthetic data in our earlier blogs. There are other routes to creating training sets. Fable data is laser focused on correctly classifying merchant transaction string patterns in anonymised consumer credit and debit card data. This blog describes...

Data Science

TV and takeaways

The primary application of our data is the low latency read we give on daily sales at hundreds of merchants across Europe. We provide contextual insight as well. Through our anonymised consumer spend panel, we can discover which merchants are more likely to be shopped together. A simple way to understand this is an analogy...

Data Science

MCC

The MCC is much more than a fancy dress club for the custodians of the Home of Cricket. Card issuers use a Merchant Category Code to classify a business based on the goods and services it sells. Builder’s merchants, opticians and confectionary vending machines all have MCCs. Payment networks also use the MCC to set...

Data Science

The Synthetic Data Generation

Improving a model using synthetic training data Any form of training requires good examples of what is to be learnt, training a machine learning model is no different. The quality of the understanding increases with the quantity and variety of relevant examples that are available. Sometimes however, there may not be a sufficiently large volume...

Data Science

Merchant Location: Filling in the gaps

In our earlier blogs we’ve discussed creating a training data set and modelling to predict the merchant based on the transaction string. This gets us to a position where we know the date, amount and merchant name for many transactions, but only have partial data on location for some purchases. Merchant location is valuable information....

Data Science

Smells like Teem Spirits

Great modelling is dependent on a great data set to train a model on. Contrary to all the advanced AI guff you see on LinkedIn, this requires hard graft, domain knowledge and initiative. There is no magic AI button to press when you leave the office and a model to use when you come back...

Data Science