
<html>

<head>

<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">

</head>

<body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space; color: rgb(0, 0, 0); font-size: 14px; font-family: Calibri, sans-serif;">

<div><br>

</div>

<span id="OLK_SRC_BODY_SECTION">

<div dir="ltr">

<div class="gmail_quote">

<div dir="ltr"><font color="#ff0000" style="background-color:rgb(255,255,255)">On behalf of the organizing team of The 2018 Choice Prediction Competition:</font>

<div>

<div class="gmail_quote">

<div dir="ltr">

<div class="gmail_quote"><br>

</div>

<div class="gmail_quote">******************************<br>

<br>

<div dir="ltr">

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="margin:0cm 0cm 0.0001pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif">Hi: We invite you to participate in the

<b>2018 choice prediction competition</b> <b>(“CPC18”) for human decision making</b>. The main goal of this competition is to improve our understanding of the ways by which behavioral decision research can contribute to the derivation of useful predictions

 of human decision making, above and beyond what is possible using data-driven machine learning tools (if at all possible). </span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="margin:0cm 0cm 0.0001pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif"><br>

</span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="margin:0cm 0cm 0.0001pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif">CPC18 distinguishes between two very different prediction tasks: predicting the aggregate population behavior in an unfamiliar choice problem, and predicting the individual behavior in a familiar choice

 problem. Specifically, CPC18 includes two parallel competition tracks, and you are invited to participate in either one, or better yet, in both. A second goal of the competition is to then understand what type of models are better suited to handle each type

 of task.</span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif">The rules of the competition and further details are given in <a href="https://cpc18.wordpress.com/" target="_blank">https://cpc18.wordpress.com</a><wbr>. A white paper summarizing the current stage

 of the competition is provided <a href="https://cpc18.files.wordpress.com/2018/01/cpc18-white-paper.pdf" target="_blank">here</a>. The deadline for final submissions is <span class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-aqj">May

 12, 2018</span> (but for one of the tracks, a partial submission must be made by <span class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-aqj">May 8</span><sup>th</sup>; see website for details). To compete, you are required

 to register by <span class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-aqj">April 10</span><sup>th</sup>.</span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif">As in <a href="http://oriplonsky.com/wp-content/uploads/2017/09/Erev-et-al-2017.pdf" target="_blank">

some</a> of the previous choice prediction competitions, the prize for the winners is an invitation to be a co-author of the paper that summarizes the competition.</span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="margin:0cm 0cm 0.0001pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif">The competition’s basic idea is as follows. We previously collected a large dataset of human choices between monetary gambles, under risk and under ambiguity, with and without feedback. This dataset

 includes over 500,000 individual consequential choices. Almost all of this data is publicly available at <a href="https://zenodo.org/record/845873#.WeDg9GhSw2x" target="_blank">https://zenodo.org/record/8<wbr>45873#.WeDg9GhSw2x</a>, and can (and probably should)

 be used to develop and train your predictive models. <span></span></span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="margin:0cm 0cm 0.0001pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif"><br>

</span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="margin:0cm 0cm 0.0001pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif">In those experiments, each decision maker faced many problems, and the two tracks differ with respect to the exact prediction challenge:</span><span style="font-family:Arial,sans-serif;font-size:11pt"> </span><br>

</p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif">In track “<b>Individual behavior, familiar problems</b>” the task is to predict the individual behavior of a small portion of these decision makers in some of the problems they faced. Therefore, a small

 portion of the data already collected will be used as the competition data in that track and is thus not available. The goal in this track is to predict, as accurately as possible, the individual behavior reflected in that data. </span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-family:Arial,sans-serif;font-size:11pt">In track "</span><b style="font-family:Arial,sans-serif;font-size:11pt">Aggregate behavior, unfamiliar problems</b><span style="font-family:Arial,sans-serif;font-size:11pt">” the task is to predict the

 aggregate choice rates in a new experiment with new problems that we will run (during March-April 2018). As in some of the previous choice prediction competitions, the submissions should be computer programs that read the parameters of the choice problems

 as input, and derive the predicted choice rates as output.</span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-family:Arial,sans-serif;font-size:11pt">We hope that you are up for the challenge!</span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="margin:0cm 0cm 0.0001pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif"><span> </span></span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="margin:0cm 0cm 0.0001pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif">The organizing team,<span></span></span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="margin:0cm 0cm 0.0001pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif">Ori Plonsky, Reut Apel, Ido Erev, Eyal Ert, and Moshe Tennenholtz<span></span></span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="margin:0cm 0cm 0.0001pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif"><span> </span></span></p>

<p class="m_5223256524593811671gmail-m_-5709760668539444704m_7130698862925417551gmail-m-578302436408794247gmail-msonormal" style="margin:0cm 0cm 0.0001pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial">

<span style="font-size:11pt;font-family:Arial,sans-serif">With apologies for cross-posting.<span></span></span></p>

</div>

</div>

<br>

</div>

</div>

<br>

</div>

</div>

</div>

<br>

</div>

</span>

</body>

</html>