BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CFP.DEV//CFP.DEV shortcodes//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Voxxed Days Ticino
X-WR-RELCALID:c426493a-54d4-472b-b975-6f3aaa7163fa
X-WR-TIMEZONE:Europe/Zurich
BEGIN:VEVENT
UID:cfp-1151-7718@cfp.dev
DTSTAMP:20260920T150246Z
SEQUENCE:0
STATUS:CONFIRMED
DTSTART:20250117T121000Z
DTEND:20250117T125500Z
SUMMARY:Information Reliability Service - a novel approach to fraud detecti
 on
DESCRIPTION:Over the past years\, criminal activities on the Swiss Post por
 tal have amounted to approximately 5 million Swiss Francs per year . Crimi
 nal organizations and their activities have become increasingly sophistica
 ted and organized over time\, with cybercrime remaining a significant conc
 ern for online retailers and services.In this presentation we address the 
 challenges of fraud detection and imbalanced datasets\, outlining the proc
 edures implemented to manage data access at an enterprise level within Swi
 ss Post. We present a machine learning approach to detect potential fraudu
 lent addresses\, preventing the activation of an account when risk is iden
 tified. Our innovative strategy employs a contextual Multi-Armed Bandit (M
 AB) model\, trained on shipment data and expert fraud evidence\, to take a
 ctions that maximize rewards by minimizing potential fraud cases. This nov
 el approach\, leveraging artificial intelligence and modern reinforcement 
 learning techniques\, is fully hosted on a cloud platform\, allowing for o
 n-demand scaling based on specific time requirements.We explore innovative
  machine learning approaches\, including MLOps and our contextual MAB-base
 d strategy\, discussing their implementation and benefits. The empirical r
 esults\, based on real-world data from Swiss Post logistic services\, demo
 nstrate that we can successfully identify a portion of the fraudulent addr
 esses with the ability to improve our algorithm over time through expert f
 eedback. These promising outcomes pave the way for future deployment in Sw
 iss Post&#39\;s production environment.We delve into the integration of ou
 r solution within a large-scale enterprise setting\, emphasizing the role 
 of Continuous Integration and Continuous Deployment (CI/CD) pipelines in m
 aintaining and improving the system.\nSpeakers: Giovanni Degiorgi\nTrack: 
 Data & AI
URL:https://vdt25.voxxeddays.ch/talk/information-reliability-service-a-nove
 l-approach-to-fraud-detection/
LOCATION:Room C\nPalazzo dei Congressi\nLugano\, Switzerland
CATEGORIES:Data & AI
END:VEVENT
END:VCALENDAR