<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Python on Harshvardhan</title>
    <link>/categories/python/</link>
    <description>Recent content in Python on Harshvardhan</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Mon, 21 Aug 2023 00:00:00 +0000</lastBuildDate>
    <atom:link href="/categories/python/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>ML Forecasting at HP Inc.</title>
      <link>/hp23/</link>
      <pubDate>Mon, 21 Aug 2023 00:00:00 +0000</pubDate>
      <guid>/hp23/</guid>
      <description>Creating ML demand forecast for print products at HP Inc. using LightGBM and pushing it to production for wide adoption.</description>
    </item>
    <item>
      <title>End-to-End Inventory Prediction and Contract Allocation for Guaranteed Delivery Advertising</title>
      <link>/kdd2023talk/</link>
      <pubDate>Mon, 07 Aug 2023 16:00:00 +0000</pubDate>
      <guid>/kdd2023talk/</guid>
      <description>We proposed a novel end-to-end approach, the Neural Lagrangian Selling (NLS) model, to improve Guaranteed Delivery (GD) advertising by concurrently predicting ad impression inventory and optimizing contract allocation</description>
    </item>
    <item>
      <title>End-to-End Inventory Prediction and Contract Allocation for Guaranteed Delivery Advertising</title>
      <link>/kdd2023/</link>
      <pubDate>Wed, 07 Jun 2023 00:00:00 +0000</pubDate>
      <guid>/kdd2023/</guid>
      <description>We proposed a novel end-to-end approach, the Neural Lagrangian Selling (NLS) model, to improve Guaranteed Delivery (GD) advertising by concurrently predicting ad impression inventory and optimizing contract allocation. The model incorporates a differentiable Lagrangian layer and a graph convolutional neural network to enable direct optimization of allocation regret and effective handling of various allocation targets and constraints. &#xA;&lt;a href=&#34;https://www.harsh17.in/docs/kdd2023/E2E_Paper.pdf&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;🔗 PDF&lt;/a&gt;</description>
    </item>
    <item>
      <title>Predicting Race, Age and Gender from Face: A Small-sample Example with Encoding</title>
      <link>/predicting-race-age-and-gender-from-face-a-small-sample-example-with-encoding/</link>
      <pubDate>Sat, 03 Jun 2023 00:00:00 +0000</pubDate>
      <guid>/predicting-race-age-and-gender-from-face-a-small-sample-example-with-encoding/</guid>
      <description>Predicting race, age and gender of faces using Variational Autoencoders and Convolutional Neural Networks.</description>
    </item>
    <item>
      <title>Crafting Conversations with GPT Personalities in Python</title>
      <link>/gpt-chatbot/</link>
      <pubDate>Sun, 09 Apr 2023 00:00:00 +0000</pubDate>
      <guid>/gpt-chatbot/</guid>
      <description>Building a customizable chatbot that brings unique characters to life</description>
    </item>
    <item>
      <title>Supply Chain Analytics at HP Inc.</title>
      <link>/hp22/</link>
      <pubDate>Mon, 31 Oct 2022 00:00:00 +0000</pubDate>
      <guid>/hp22/</guid>
      <description>Forecasting Global Print Demand Using Machine Learning</description>
    </item>
    <item>
      <title>Cheatsheet on Python</title>
      <link>/notes-on-python/</link>
      <pubDate>Tue, 08 Feb 2022 00:00:00 +0000</pubDate>
      <guid>/notes-on-python/</guid>
      <description>Some things that I&amp;rsquo;ll likely forget</description>
    </item>
    <item>
      <title>Supervised Learning Using Baysian Decision Rule</title>
      <link>/supervised-learning-using-baysian-decision-rule/</link>
      <pubDate>Tue, 07 Sep 2021 00:00:00 +0000</pubDate>
      <guid>/supervised-learning-using-baysian-decision-rule/</guid>
      <description>Python Functions for Bayesian Learning (COSC 522 Project)</description>
    </item>
  </channel>
</rss>
