<div dir="ltr"><table class="gmail-Bs gmail-nH gmail-iY gmail-bAt" cellpadding="0" style="border-spacing:0px;padding:0px;border-collapse:collapse;width:743.466px;display:block;color:rgb(32,33,36);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:medium"><tbody><tr><td class="gmail-Bu gmail-yM" style="vertical-align:top;padding:0px;width:0px;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"></td><td class="gmail-Bu gmail-bAn" style="vertical-align:top;padding:0px;display:block;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><div class="gmail-nH gmail-if" style="margin:0px 16px 0px 0px;padding:0px"><div class="gmail-nH gmail-aHU" style=""><div class="gmail-nH gmail-hx gmail-aHo" style="background-color:transparent;color:rgb(34,34,34);min-width:592px;padding:0px"><div class="gmail-nH"><div class="gmail-h7 gmail-ie gmail-nH gmail-oy8Mbf gmail-j23lnd gmail-Aqhktf" tabindex="-1" style="clear:both;padding-bottom:0px;max-width:100000px;outline:none"><div class="gmail-Bk" style="margin-bottom:0px;border-width:0px;border-top-style:solid;border-right-style:initial;border-bottom-style:initial;border-left-style:initial;border-top-color:rgb(239,239,239);border-right-color:initial;border-left-color:initial;border-bottom-color:initial;border-radius:0px;width:726.733px;float:none"><div class="gmail-G3 gmail-G2" style="padding-top:0px;background-color:transparent;border-right:0px;border-bottom:0px rgba(100,121,143,0.12);border-left:0px;border-top:none;border-radius:0px;margin-bottom:0px;margin-left:0px;margin-right:0px"><div id="gmail-:2ns"><div class="gmail-adn gmail-ads" style="border-left:none;padding:0px;display:flex"><div class="gmail-gs" style="margin:0px;padding:0px 0px 20px;width:654.744px"><div class="gmail-"><div id="gmail-:2nv" class="gmail-ii gmail-gt" style="font-size:0.875rem;direction:ltr;margin:8px 0px 0px;padding:0px"><div id="gmail-:2nu" class="gmail-a3s gmail-aXjCH" style="overflow:hidden;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;font-size:small;line-height:1.5;font-family:Arial,Helvetica,sans-serif"><div dir="ltr"><div><div style="box-sizing:inherit;font-family:Mallory,Verdana,Arial,Helvetica,sans-serif;font-size:17px"><span style="box-sizing:inherit"><span style="box-sizing:inherit"><span style="box-sizing:inherit"><h1 style="box-sizing:inherit;font-weight:300;padding:0px;font-feature-settings:"kern","liga","dlig";font-size:1.76471em;line-height:normal;font-stretch:normal;color:rgb(0,60,118);text-transform:uppercase;display:inline-block">S&DS|CS JOINT SEMINAR, BERK <span class="gmail-il">USTUN</span></h1></span></span></span><span style="box-sizing:inherit;margin-left:5px"><span style="box-sizing:inherit"><span style="box-sizing:inherit">Harvard University</span></span></span><div style="box-sizing:inherit"><div style="box-sizing:inherit"><div style="box-sizing:inherit;font-size:20px;font-weight:600;line-height:1.2;margin-bottom:1em;margin-top:0.5em">Designing for the Last Mile in Machine Learning</div></div></div></div><div style="box-sizing:inherit;float:left;width:auto;padding-right:14.4844px;max-width:30%;font-family:Mallory,Verdana,Arial,Helvetica,sans-serif;font-size:17px"><div style="box-sizing:inherit"><div style="box-sizing:inherit"><div style="box-sizing:inherit"><img src="https://statistics.yale.edu/sites/default/files/styles/user_picture_node/public/bio-photo.jpg?itok=MrZxZFCJ" width="400" height="480" alt="" class="gmail-CToWUd gmail-a6T" tabindex="0" style="cursor: pointer; outline: 0px; box-sizing: inherit; border: 0px; max-width: 100%; height: auto; vertical-align: bottom;"></div></div></div></div><div style="box-sizing:inherit;float:left;width:auto;max-width:65%;padding-left:21.7344px;font-family:Mallory,Verdana,Arial,Helvetica,sans-serif;font-size:17px"><div style="box-sizing:inherit"><div style="box-sizing:inherit"><div style="box-sizing:inherit;color:rgb(0,60,118);font-size:18px;line-height:1.4"><span style="box-sizing:inherit">Wednesday, February 26, 2020<span style="box-sizing:inherit;float:left;width:427.562px"><span style="box-sizing:inherit">4:00PM</span> to <span style="box-sizing:inherit">5:00PM</span></span></span></div></div></div><div style="box-sizing:inherit"><div style="box-sizing:inherit"><div style="box-sizing:inherit"><div style="box-sizing:inherit"><div style="box-sizing:inherit"><span style="box-sizing:inherit">YINS</span> <span style="box-sizing:inherit;margin-left:0.25em;font-size:0.925em;line-height:1.55;letter-spacing:0.05em;word-spacing:0.05em;text-transform:lowercase;font-feature-settings:"smcp""><a href="http://maps.google.com/?q=17+Hillhouse+Avenue%2C+Rm.+328%2C+New+Haven%2C+CT%2C+06511%2C+us" target="_blank" style="color:rgb(40,109,192);box-sizing:inherit;outline:none;line-height:inherit">see map</a> </span><div style="box-sizing:inherit">17 Hillhouse Avenue, Rm. 328</div><span style="box-sizing:inherit">New Haven</span>, <span style="box-sizing:inherit">CT</span> <span style="box-sizing:inherit">06511</span></div></div></div></div></div><div style="box-sizing:inherit"><div style="box-sizing:inherit"><div style="box-sizing:inherit"><a href="https://www.berkustun.com/" target="_blank" style="color:rgb(0,60,118);box-sizing:inherit;text-decoration-line:none;outline:none;line-height:1.5;font-size:16px">Website</a></div></div></div></div><div style="box-sizing:inherit;clear:both;padding-top:15px;font-family:Mallory,Verdana,Arial,Helvetica,sans-serif;font-size:17px"><div style="box-sizing:inherit"><div style="box-sizing:inherit;font-weight:bold">Information and Abstract: </div><div style="box-sizing:inherit"><div style="box-sizing:inherit"><p style="box-sizing:inherit;margin:0px 0px 1em;padding:0px">Machine learning is now a general-purpose technology. In many domains, we can build models to support important decisions or automate routine tasks. Yet we may not reap their benefits due to disuse, or even inflict harm due to misuse. In this talk, I will present methodological advances that address these “last mile” challenges. First, I will describe a method to learn simple risk scores that are readily adopted for medical decision support, and discuss applications to adult ADHD diagnosis and ICU seizure prediction. Next, I will describe how machine learning models may harm individuals in consumer-facing applications by violating their right to autonomy. I will then introduce the notion of “recourse” and formalize methods to prevent such harms without interfering in model development.</p><p style="box-sizing:inherit;margin:0px 0px 1em;padding:0px"><strong style="box-sizing:inherit">Bio: </strong><a href="https://nam05.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.berkustun.com%2F&data=02%7C01%7Cdawn.hemstock%40yale.edu%7C8c929108844b42742a5108d7af302e53%7Cdd8cbebb21394df8b4114e3e87abeb5c%7C0%7C0%7C637170493785328756&sdata=znhsnEe%2BSrwNf4aMkLD5YR8Uue7MVPeFEOYkvyG%2BTUo%3D&reserved=0" rel="nofollow" target="_blank" style="color:rgb(40,109,192);box-sizing:inherit;outline:none;line-height:inherit;word-break:break-word">Berk <span class="gmail-il">Ustun</span></a> is a postdoc at the Harvard Center for Research on Computation and Society. His research interests are in machine learning, optimization, and human-centered design. In particular, he focuses on developing methods to promote the adoption and responsible use of machine learning in domains such as medicine, consumer finance, and criminal justice. </p><p style="box-sizing:inherit;margin:0px 0px 1em;padding:0px">Berk has built machine learning systems that are now used by major healthcare providers for hospital readmissions prediction, ICU seizure prediction, and adult ADHD screening. His work has been covered by various media outlets, including NPR and Wired, and has won major awards, including the INFORMS Informative Applications in Analytics Award in 2016 and 2019, and the INFORMS Computing Society Best Student Paper.</p><p style="box-sizing:inherit;margin:0px 0px 1em;padding:0px">Berk holds a PhD in Electrical Engineering and Computer Science from MIT, an MS in Computation for Design and Optimization from MIT, and BS degrees in Operations Research and Economics from UC Berkeley. </p><p style="box-sizing:inherit;margin:0px 0px 1em;padding:0px">For links to papers, videos, and software, see: <a href="https://nam05.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.berkustun.com%2F&data=02%7C01%7Cdawn.hemstock%40yale.edu%7C8c929108844b42742a5108d7af302e53%7Cdd8cbebb21394df8b4114e3e87abeb5c%7C0%7C0%7C637170493785328756&sdata=znhsnEe%2BSrwNf4aMkLD5YR8Uue7MVPeFEOYkvyG%2BTUo%3D&reserved=0" rel="nofollow" target="_blank" style="color:rgb(40,109,192);box-sizing:inherit;outline:none;line-height:inherit;word-break:break-word">https://www.berkustun.com</a>.</p></div></div></div></div></div></div><div class="gmail-yj6qo"></div><div class="gmail-adL"></div></div></div><div class="gmail-hi" style="border-bottom-left-radius:1px;border-bottom-right-radius:1px;padding:0px;width:auto;background:rgb(242,242,242);margin:0px"></div></div></div><div class="gmail-ajx" style="clear:both"><br></div></div></div></div></div></div></div></div></div></div></td><td class="gmail-Bu gmail-yM" style="vertical-align:top;padding:0px;width:0px;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><div class="gmail-nH" style="width:0px"></div></td></tr></tbody></table><br class="gmail-Apple-interchange-newline"></div>