<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" ><generator uri="https://jekyllrb.com/" version="3.10.0">Jekyll</generator><link href="https://jiajumiao.github.io/feed.xml" rel="self" type="application/atom+xml" /><link href="https://jiajumiao.github.io/" rel="alternate" type="text/html" /><updated>2025-11-12T22:36:01-05:00</updated><id>https://jiajumiao.github.io/feed.xml</id><title type="html">Jiaju Miao</title><subtitle>AI/Finance • Model Risk • Research • Boxing</subtitle><author><name>Jiaju Miao</name></author><entry><title type="html">ICAIF 2025 — Oral Presentation: Online Ensemble Learning for Sector Rotation</title><link href="https://jiajumiao.github.io/papers/icaif2025-announcement/" rel="alternate" type="text/html" title="ICAIF 2025 — Oral Presentation: Online Ensemble Learning for Sector Rotation" /><published>2025-11-04T00:00:00-05:00</published><updated>2025-11-04T00:00:00-05:00</updated><id>https://jiajumiao.github.io/papers/icaif2025-announcement</id><content type="html" xml:base="https://jiajumiao.github.io/papers/icaif2025-announcement/"><![CDATA[<p>I’m delighted to share that my paper <strong>“Online Ensemble Learning for Sector Rotation: A Gradient-Free Framework”</strong><br />
(co-authored with <strong>P. Polak</strong>) has been accepted for <strong>oral presentation</strong> at the<br />
<strong>6th ACM International Conference on AI in Finance (ICAIF ’25)</strong>, to be held in <strong>Singapore</strong>.</p>

<p>This paper introduces a <strong>gradient-free online ensemble learning framework</strong> for <strong>sector rotation</strong> —<br />
a gradient-free online ensemble learning algorithm that dynamically combines forecasts from a heterogeneous set of machine learning models based on their recent predictive performance.</p>

<p>The work was accepted for <strong>oral presentation</strong> with a <strong>15.5% acceptance rate</strong>,<br />
highlighting its recognition among competitive AI &amp; Finance submissions.</p>

<hr />

<h3 id="️-presentation-details">🎙️ <strong>Presentation Details</strong></h3>

<p><strong>Session:</strong> <em>Time-Series Modeling and Forecasting</em><br />
<strong>Type:</strong> Oral Session<br />
<strong>Date:</strong> <strong>Tuesday, November 18, 2025</strong><br />
<strong>Time:</strong> <strong>10:50 AM – 11:10 AM (Singapore Time)</strong><br />
<strong>Location:</strong> <em>Ballroom 4</em><br />
<strong>Conference:</strong> <em>6th ACM International Conference on AI in Finance (ICAIF ’25)</em></p>

<h4 id="subsession-schedule">Subsession Schedule:</h4>
<p>| Time (SGT) | Presentation Title |
|————-|——————–|
| 10:30 – 10:50 AM | DeltaLag: Learning Dynamic Lead–Lag Patterns in Financial Markets |
| <strong>10:50 – 11:10 AM</strong> | <strong>Online Ensemble Learning for Sector Rotation: A Gradient-Free Framework</strong> <em>(J. Miao, P. Polak)</em> |
| 11:10 – 11:30 AM | Factor-Driven Network Informed Restricted Vector Autoregression |</p>

<hr />

<p>📄 <strong>Authors:</strong> Jiaju Miao &amp; Pawel Polak<br />
🔗 <strong>Paper:</strong> <a href="https://arxiv.org/pdf/2304.09947v2">arXiv PDF</a><br />
📅 <strong>Conference:</strong> ICAIF 2025, Singapore<br />
🎤 <strong>Format:</strong> Oral Presentation — <em>Time-Series Modeling and Forecasting</em> (Ballroom 4)</p>

<hr />

<p>Thank you to the ICAIF 2025 program committee for the opportunity to present this work.<br />
I look forward to sharing more details, slides, and insights from the conference soon!</p>]]></content><author><name>Jiaju Miao</name></author><category term="papers" /><category term="ICAIF" /><category term="conference" /><category term="ensemble" /><category term="finance" /><category term="presentation" /><category term="forecasting" /><summary type="html"><![CDATA[I’m delighted to share that my paper “Online Ensemble Learning for Sector Rotation: A Gradient-Free Framework” (co-authored with P. Polak) has been accepted for oral presentation at the 6th ACM International Conference on AI in Finance (ICAIF ’25), to be held in Singapore.]]></summary></entry></feed>