<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>tress Tracker</title>
    <link>https://communities.sas.com/kntur85557/tracker</link>
    <description>tress Tracker</description>
    <pubDate>Sun, 19 Apr 2026 05:21:48 GMT</pubDate>
    <dc:date>2026-04-19T05:21:48Z</dc:date>
    <item>
      <title>Need Advice on Handling High-Dimensional Data in Data Science Project</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/Need-Advice-on-Handling-High-Dimensional-Data-in-Data-Science/m-p/926214#M10766</link>
      <description>&lt;P&gt;Hey everyone,&lt;/P&gt;&lt;P&gt;I’m relatively new to data science and currently working on a project that involves a dataset with over 60 columns. Many of these columns are categorical, with more than 100 unique values each.&lt;/P&gt;&lt;P&gt;My issue arises when I try to apply one-hot encoding to these categorical columns. It seems like I’m running into the curse of dimensionality problem, and I’m not quite sure how to proceed from here.&lt;/P&gt;&lt;P&gt;I’d really appreciate some advice or guidance on how to effectively handle high-dimensional data in this context. Are there alternative encoding techniques I should consider? Or perhaps there are preprocessing steps I’m overlooking?&lt;/P&gt;&lt;P&gt;Any insights or tips would be immensely helpful.&lt;/P&gt;&lt;P&gt;Thanks in advance!&lt;/P&gt;</description>
      <pubDate>Sun, 28 Apr 2024 11:57:46 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/Need-Advice-on-Handling-High-Dimensional-Data-in-Data-Science/m-p/926214#M10766</guid>
      <dc:creator>tress</dc:creator>
      <dc:date>2024-04-28T11:57:46Z</dc:date>
    </item>
  </channel>
</rss>

