<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>machine learning on Yazid&#39;s Blog</title>
    <link>https://yazidk.netlify.app/tags/machine-learning/</link>
    <description>Recent content in machine learning on Yazid&#39;s Blog</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 16 Jul 2021 00:00:00 +0000</lastBuildDate><atom:link href="https://yazidk.netlify.app/tags/machine-learning/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Rossman Store Sales Prediction</title>
      <link>https://yazidk.netlify.app/2021/07/16/rossman-store-sales-prediction/</link>
      <pubDate>Fri, 16 Jul 2021 00:00:00 +0000</pubDate>
      
      <guid>https://yazidk.netlify.app/2021/07/16/rossman-store-sales-prediction/</guid>
      <description>The following project studies a Kaggle use case to predict sales volume for Rossman drug store. An overview of the predictors used, evaluation metrics and leaderboards and be found Here
Rossmann operates over 3,000 drug stores in 7 European countries. Currently, Rossmann store managers are tasked with predicting their daily sales for up to six weeks in advance. Store sales are influenced by many factors, including promotions, competition, school and state holidays, seasonality, and locality.</description>
    </item>
    
    <item>
      <title>Twitter text analysis</title>
      <link>https://yazidk.netlify.app/2019/08/19/machine-learning-twitter-analysis/</link>
      <pubDate>Mon, 19 Aug 2019 00:00:00 +0000</pubDate>
      
      <guid>https://yazidk.netlify.app/2019/08/19/machine-learning-twitter-analysis/</guid>
      <description>Twitter hosts the perfect enviroment for text analysis, the icing on the cake is the rtweet package. The rtweet package provides an API to gather text data on twitter easily, it contains an option to specify the geographical location. Every tweet that has the keyword “machine learning” as a plain text or a hashtag is collected and tokenized (split up to individual words), common words such as “the”, “of” and “to” are removed since they are not useful and do not add value to the analysis.</description>
    </item>
    
  </channel>
</rss>
