Contact us









    Blog

    /Blog/

    Assembly line for predictive models

    Predictive models in banks, lenders, insurance companies and others are notorious for being extremely slow to produce and launch. This is the result of many reasons, none of them directly related to the technical details of building a predictive model. Some of the reasons are: Absence of direct linkage (code) between research model and the deployed model (often written in different languages!) Absence of a unified data lake holding both the training data as well as the new data coming from production. The need for full data lineage detailing the source and usage of every piece of data The need to go through a set of regulatory procedures and approvals These reasons (and more) make the modeling effort in these organizations a one-off project where each iteration or versions of the same model feels like a whole new modelling project. This in turn leads to shockingly slow modelling iterations. How slow? Some organisations require as much as six months to build and sometimes even much longer to launch a new [...]

    By | October 1st, 2020|General, Product|0 Comments

    Data augmentation in credit risk management: See your data through AR glasses

    Have you ever tried augmented reality glasses? They let you see reality, and at the same time show you additional data that’s relevant for that reality. In a nutshell, this is what data augmentation does to your credit risk models. Data augmentation and credit risk management We’ve written about the various ways banks are leveraging AI before. Machine learning is making credit risk modelling more accurate and allows you to draw the right conclusions from heaps of data.  Data augmentation will assist you to create the most accurate ML models. It is the process of adding more layers of (usually) external data and including it in your machine learning training set.  Many banks still base their models on a limited data set. They look at their customers using data that originated from the application requests and from data warehouse databases. Sometimes they add only FICO or other agency’s scores. This is highly limiting and hurts the models' accuracy. The data is not utilized to the full extent in predictive analytics. [...]

    By | August 10th, 2020|General|0 Comments

    Seeing the full credit risk picture using external data sources

    There is an old parable about a group of blind men who have never seen an elephant before. When they first encounter one, each one feels a different part of it, like the trunk or the ears. Each one in turn describes the beast in a completely different way. There are several lessons that can be learned from this fable. What I take from it is to always remember to see the bigger picture.  To always ask “what am I missing?” and include all the data points. This is especially true when it comes to credit risk modelling, and the use of varied data sources. If you only rely on internal data sources, you’re definitely not seeing the full picture. The result? You are either exposing yourself to more risk than intended, or are leaving money on the table.  Using the right sources, the right way You must have full control on which data points and data sources are in use, as the GDPR and similar regulations require it. In [...]

    By | June 23rd, 2020|General|0 Comments

    Different challenges, one solution: Credit risk management for banks and fintech

    A guest post from Dr. Martin Seeger, Credit Risk Manager and Data Scientist, BeeEye's Advisory Board member Credit risk modeling poses different challenges to banks and Fintech companies. A solution can lay in a modeling platform that caters for both In the context of credit risk modeling, traditional financial institutions (e.g., banks, insurers) and Fintech companies both have very specific risk profiles they need to maintain. For both, the cost of inaccuracy is incredibly high.  However, banks and fintech companies face two very distinct challenges when it comes to achieving this covetable accuracy. Banks’ barriers Updating your platform once in a blue moon If you’re a risk analyst or modeller in a traditional financial institution, you are likely all too familiar with regulations’ impact on internal processes. Specifically, how regulations stretch out these processes in a way that may hurt modeling accuracy. Usually banks perform rating model validations only once a year due to the complexity of the processes regulations require. When they do, validation data may be a year [...]

    By | May 31st, 2020|General|0 Comments
    ×

    HOW BANKS ARE LEVERAGING AI

    Read our white paper

    The rise in available data and access to computing power is challenging banks to look towards artificial intelligence and machine learning as the solution.

    HOW BANKS ARE LEVERAGING AI

    There is a new generation of products that are built to overcome the challenges that the first generation of AI solutions didn’t solve and help innovators and risk managers find new technologies to gain a competitive advantage.