In the present day we use machine learning for sensitive tasks that require models to be both understandable and robust. Although traditional models such as decision trees are understandable, they suffer from adversarial attacks. When a decision tree is used to differentiate between a user's benign and malicious behavior, an adversarial attack allows the user to effectively evade the model by perturbing the inputs the model receives. We can use algorithms that take adversarial attacks into account to fit trees that are more robust. In this work we propose an algorithm that is two orders of magnitudes faster and scores 4.3% better on accuracy against adversaries moving all samples than the state-of-the-art work while accepting an intuitive and permissible threat model. Where previous threat models were limited to distance norms, we allow each feature to be perturbed with a user-specified threat model specifying either a maximum distance or constraints on the direction of perturbation. Additionally we introduce two hyperparameters rho and phi that can control the trade-off between accuracy vs robustness and accuracy vs fairness respectively. Using the hyperparameters we can train models with less than 5% difference in false positive rate between population groups while scoring on average 2.4% higher on accuracy against adversarial attacks. Lastly, we show that our decision trees perform similarly to more complex random forests of fair and robust decision trees.

ING wants to offer their customers the best experience possible. To achieve this goal, ING’s Customer Journey Experts (CJEs) constantly map and analyze the way customers use ING services in a Customer Journey Map. These maps however, are hard to share and collaborate on. ING needs an online tool in which they can, together with multiple people, build and maintain Customer Journey Maps. During our research phase we visited many different squads and found out that no single solution fits all needs. That is why we made our tool as customizable as possible with features such as: colors, text decorations, highlighting and templates. We worked in bi-weekly sprints for which we selected work from a top 50 issues board that we ordered by importance and difficulty. The final product, Mapp , allows CJEs to define, share and collaborate on customer journeys. CJEs can illustrate their customer’s steps using text, images, emotions, checkboxes andtimelines. TosharetheirworktheycanexportasPDFandprintinanysize. Andfinallytocollaborate they can simply share their journey’s URL. The product was user validated during a large midterm and endterm test, as well as during short weekly tests. All of the chapter leads we talked to were super excited and are soon marketing the product in their teams!