We are

Career at

News at

Techmonitor

  • Artificial intelligence in banking: Deep learning vs. gradient boosting
    Customer behaviours in retail banking have changed in recent years. Since 2014, customer willingness to switch bank accounts has doubled. Banks have various response options to sustain customer loyalty. However, those potentially migrating customers need to be identified beforehand. This can be done via AI-driven analysis of master data and transaction data. In 2016, Spanish bank Banco Santander published a public tender for this customer „churn case“, which was analysed by more than 5,000 data analysis teams worldwide. COREai participated in the tender and tested the two AI models gradient boosting and deep learning, comparing their results on various dimensions. The article elaborates on COREai‘s analysis strategy. In terms of the results, gradient boosting surpasses deep learning regarding its predictive accuracy and performance. The comparison was quantified by using a misclassification rate, which represents the proportion of incorrectly predicted data points and customers. During testing the deep learning method misprognosed 23% of the data, while gradient boosting only came to wrong results in 3.3% of the cases. Additionally, gradient boosting outperformed deep learning with shorter learning and prediction times. Also in terms of interpretability of the results, gradient boosing excels over deep learning, due to its easier interpretable functional structure using individual decision trees instead of one complex layered neural network, as is the case with deep learning. This potentially enables more effective drawing of conclusions regarding the reasons of a customer’s account termination. Taking those findings into account, the authors argue that gradient boosting is a more promising solution for use cases, as the one defined by Banco Santander. Nonetheless, no general statements about the dominance of either of the models can be made, as it is dependent of the use case’s data patterns. For example, deep learning remains unchallenged in terms of image or speech recognition.
  • Security in agile procedures
    Software and infrastructure projects are subject to fundamental change. The trend today is towards small, agile teams that work independently of each other and often spatially separated from each other. They develop completed subprograms that communicate with each other via coordinated interfaces and thus form an overall system. The agile approach brings with it fundamental advantages that are particularly useful in complex projects. For decades, attempts have been made to reconcile security and features. From our point of view, one step along this path is the integration of the Security Ambassador function into the agile development teams. Starting with Sprint zero, the ambassador works on an equal footing with the functional requirements at the product goal and has overall external responsibility for product safety. This addition to the agile model combines an agile approach with a holistic view of security based on the experience of our projects in recent years. By consistently treating the security requirements as equal targets, the security of a system can be assessed and therefore certified; a characteristic of supervision that is now required. Overall, IT security becomes a measurable quality feature such as functional product features that can be transported to the outside world and monetarized as a product feature.
  • Key Factor Motivation - Manage More Complex Software Development Projects
    Agile methods are a key determent in software development. The successful application of the agile methodology, such as Scrum, DSDM or Kanban is highly dependent on the (intrinsic) motivation of the parties involved in software development projects. Hence, maintaining, controlling and increasing motivation becomes inevitably throughout any project. In order to guarantee a high level of motivation, three consecutive elements have been found to be crucial. Nevertheless, a high degree of transparency has been proven to be the main condition to guarantee the following elements in motivation management. It has been previously been proven that 1. Establish an overarching, long-term project vision 2. Concretize stages and milestones and 3. Illustrating dependencies transparently, are needed to maintain employee’s motivation.