<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Projects on Sohaib Panwala</title>
    <link>https://Sohaibpanwala.github.io/post/</link>
    <description>Recent content in Projects on Sohaib Panwala</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Thu, 02 Mar 2017 12:00:00 -0500</lastBuildDate><atom:link href="https://Sohaibpanwala.github.io/post/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Unsupervised Machine Learning - Segmenting a Bank&#39;s customers</title>
      <link>https://Sohaibpanwala.github.io/post/project-2/</link>
      <pubDate>Fri, 20 Aug 2021 11:00:59 -0400</pubDate>
      
      <guid>https://Sohaibpanwala.github.io/post/project-2/</guid>
      <description>I was provided with a series of csv files about the banking habits of customers: information about their chequing accounts, saving accounts and general other transaction data. I was also given information about the demographics of the customers - generic descriptors such as age, marital status, yearly income, gender and city/state.
At this point i had to clean the data i was provided with - find and rectify typos in the messy data, impute missing values, encode the categorical variables and so on.</description>
    </item>
    
    <item>
      <title>Analytics of Retail Data</title>
      <link>https://Sohaibpanwala.github.io/post/project-1/</link>
      <pubDate>Sun, 15 Aug 2021 10:58:08 -0400</pubDate>
      
      <guid>https://Sohaibpanwala.github.io/post/project-1/</guid>
      <description>I obtained generated retail data from Keith Galli, the dataset obtained had about 200,000 orders with varying different aspects about them. From this, i performed feature engineering and data cleaning in extracting date, time data and locations to give me further insights on the best revenue generating months/cities. Under certain assumptions, I was able to model the optimal time to advertise.
Furthermore, i went and extracted key business insights such as the best selling products and the best complements of products bought (i.</description>
    </item>
    
  </channel>
</rss>
