Interview with – Kristina Reicher
summary
Koyo's Consulting applies ML/AI to banking credit scoring and claims digital footprint variables like shopping cadence, email patterns and mobile device signals are cheap to collect, add measurable predictive power, and can predict default without credit history for thin‑file customers used by fintech and buy‑now‑pay‑later products. Work focuses on data engineering, cleaning and explainable models because regulators demand reasons, and ethical/consent issues remain unresolved even though prototypes show useful accuracy gains.
AI-written summary · about
chapters (5)
- 0:00Start
- 0:24How did you come to be involved in Business Intelligence? And what are your main interests related to Data Science?
- 3:24Can you describe your usual day as a Business Intelligence Consultant? How important are data engineering and data science in your daily operations?
- 6:16As you are representative of our Gold Sponsor Koyo's consulting, could you please elaborate on what Koyo's consulting do?
- 10:04Do you have anything to say for the future attendees, how to encourage them, and what do you have to say to other companies to support this kind of initiative?
related talks
22mUsing data to innovate credit decisioning for Small-to-Medium Enterprises
39mMachine Learning in Financial Credit Risk Assessment
29mAI - Digital (r)evolution in banking
35mPanel | Data Revolution: A New Hope for Fair Creditworthiness
01h 03mAI Innovation for a Smarter Financial Ecosystem
41mAI For All: Enhancing Digital Financial Services using Data Science
58mNew-type Scoring Models: Analyzing Customer Actions
27mData Science and ML with an emphasis on Banking...