<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Innosuisse |</title><link>https://pc.inf.usi.ch/tags/innosuisse/</link><atom:link href="https://pc.inf.usi.ch/tags/innosuisse/index.xml" rel="self" type="application/rss+xml"/><description>Innosuisse</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 01 Sep 2025 00:00:00 +0000</lastBuildDate><image><url>https://pc.inf.usi.ch/media/icon_hu_3e3e1276701fcef7.png</url><title>Innosuisse</title><link>https://pc.inf.usi.ch/tags/innosuisse/</link></image><item><title>XAI-FinCrime</title><link>https://pc.inf.usi.ch/projects/xai-fincrime/</link><pubDate>Mon, 01 Sep 2025 00:00:00 +0000</pubDate><guid>https://pc.inf.usi.ch/projects/xai-fincrime/</guid><description>&lt;p&gt;&lt;strong&gt;Funding:&lt;/strong&gt; Innosuisse · September 2025 – August 2028&lt;/p&gt;
&lt;p&gt;The project aims to transform financial crime prevention by leveraging machine learning, generative AI, and explainable AI (XAI) to enhance fraud detection and compliance management. It uses ML models for transactional behavior analysis and multimodal LLMs for unstructured data processing, with counterfactual explainers to improve AI decision transparency.&lt;/p&gt;
&lt;h2 id="objectives"&gt;Objectives&lt;/h2&gt;
&lt;ul&gt;
&lt;li&gt;Significantly reduce the typical False Positive rate of 95% found in current rule-based industry standards&lt;/li&gt;
&lt;li&gt;Improve F1-scores, accuracy, and True Positive rates compared to existing solutions&lt;/li&gt;
&lt;li&gt;Enhance user understanding of AI systems to reduce investigation effort per alert&lt;/li&gt;
&lt;li&gt;Validate innovations through pilot studies with financial institutions&lt;/li&gt;
&lt;/ul&gt;</description></item></channel></rss>