Resources
Highlight
All resources
-
-
-
-
-
-
-
-
-
-
-
-
-
The golden age of data in financial services
Financial services is a data-intensive industry in which banks and insurance companies have historically held large quantities of information. The development of the internet, the increase in new channels, and the introduction of technologies including cookies and trackers have helped not only to create a better user experience, but also to exponentially increase the amount of collected data, for the most part dark data. With the availability of new digital technologies and a higher degree of interconnectivity and interactions, new data sources have emerged that are a potential treasure trove for businesses. -
SMEs: last call for banks and incumbents
SMEs, and in particular micro and small companies, are an important part of the European economy. The micro and small business segment includes over 25 million companies, with a total turnover of over €10bn, and employs just under 43% of the total number of employees in the European private sector. Despite the overall size of the segment, these companies have been, up to now, challenging for banks to serve. Due to the small size of these organizations, they are often classified and treated as retail customers. This, coupled with their limited accounting and financial management capabilities, limits their ability to access finance. -
Data Driven Personalization in Banking
Currently, we live in an era where personalization has become the norm and is expected from banks, as financial services are increasingly driven by highly customized and personalized offerings from not only traditional banks, but also neo banks, FinTech’s, digital financial providers, and even companies outside of financial services such as telcos and retail companies. These opportunities are enabled by technologies, analytic capabilities and endless user information that allow providers to create such personalized experiences that customers love. -
Open your Bank to the Data
The beginning of Open Banking had a variety of industry and commercial impacts, but one of the unintended consequences in consumers’ lives was that they came to realize that their data was theirs and that they could choose who to share it with. That was catalyzed by all the campaign of awareness about the social networks scandals raised on the past, where people started to wake about what other companies where doing with their information and how their were leveraging their business models on all the metadata and insights information behind liking a photo on Instagram, reacting to a publication on Facebook or checking into a place in Foursquare. As a result, in the future, people are going to be more cautious about their personal information and their data, but they will still share it with you if you prove to them that your counterpart is worth the cost. -
Instability of LIME Explanations
Giorgio Visani
How to Deal with it? Behold the stability indices -
LIME: explain Machine Learning predictions
Giorgio Visani
Intuition and Geometrical Interpretation of LIME
-
Explainable Machine Learning
Giorgio Visani
XAI Review: Model Agnostic Tools
-
Enabling Synthetic Data adoption in regulated domains
The switch from a Model-Centric to a Data-Centric mindset is putting emphasis on data and its quality rather than algorithms, bringing forward new challenges. In particular, the sensitive nature of the information in highly regulated scenarios needs to be accounted for. Speci c approaches to address the privacy issue have been developed, as Privacy Enhancing Technologies. -
Explanations of Machine Learning predictions: a mandatory step for its application to Operational Processes
In the global economy, credit companies play a central role in economic development, through their activity of money lenders. This important task comes with some drawbacks, mainly the risk of the debtors of not being able to repay the provided credit. Therefore, Credit Risk Modelling (CRM), namely the evaluation of the probability that a debtor will not repay the due amount, plays a paramount role. -
Metrics for multi-class classification: an overview
Classification tasks in machine learning involving more than two classes are known by the name of "multi-class classification". Performance indicators are very useful when the aim is to evaluate and compare different classification models or machine learning techniques. Many metrics come in handy to test the ability of a multi-class classifier. -
OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms
Local Interpretable Model-Agnostic Explanations (LIME) is a popular method to perform interpretability of any kind of Machine Learning (ML) model. It explains one ML prediction at a time, by learning a simple linear model around the prediction. -
Statistical stability indices for LIME: obtaining reliable explanations for Machine Learning models
Nowadays we are witnessing a transformation of the business processes towards a more computation driven approach. The ever increasing usage of Machine Learning techniques is the clearest example of such trend. -
Catch Product Sheet
Standalone categorisation technology
-
Neos Product Sheet
Open Banking Suite
-
Phyon Product Sheet
The phygital onboarding
-
Remote Selling Product Sheet
Close your selling process and sign your contracts digitally
-
Catch One Pager
Standalone categorisation technology
-
Neos One Pager
Open Banking Suite
-
Phyon One Pager
The phygital onboarding
-
Remote Selling One Pager
Close your selling process and sign your contracts digitally
-
Credit Passport One Pager
SME credit scoring. Solved by Open Banking