{"id":8088,"date":"2026-03-11T10:30:17","date_gmt":"2026-03-11T05:00:17","guid":{"rendered":"https:\/\/sketharaman.com\/blog\/?p=8088"},"modified":"2026-03-05T23:49:48","modified_gmt":"2026-03-05T18:19:48","slug":"actionable-insights-from-mybar-chatgpt-data-analysis","status":"publish","type":"post","link":"https:\/\/sketharaman.com\/blog\/2026\/03\/11\/actionable-insights-from-mybar-chatgpt-data-analysis\/","title":{"rendered":"Actionable Insights From myBAR ChatGPT Data Analysis"},"content":{"rendered":"

In myBAR Data Analysis By ChatGPT<\/strong><\/a>, we saw various insights from ChatGPT based on crunching the data in myBAR dataset<\/strong> (For those who haven’t read that post, myBAR dataset contains ratings and reviews given by me to 600-odd books I’ve read in the last 15-odd years).<\/p>\n

This analysis happened on data in a spreadsheet. Some vendors call CSV \/ XLS unstructured data<\/em> whereas others call it semi-structured data<\/em>. Either way, this is a canonical example of the use of ChatGPT to conduct data analysis on non-structured<\/em> data. (Click here<\/strong><\/a> to see an example where ChatGPT did data analysis on handwritten data, which everybody would agree is unstructured data.)<\/p>\n

I was surprised that ChatGPT missed an obvious insight into my reading behavior, namely, that I’ve an overwhelming preference for fiction over non-fiction books. But, apart from that solitary error of omission, its insights were very comprehensive, spanning two categories:<\/p>\n

    \n
  1. Basic insights<\/strong><\/em>: Based on data in myBAR dataset.<\/li>\n
  2. Advanced insights<\/em><\/strong>: Based on additional data fetched by ChatGPT that was not in myBAR dataset.<\/li>\n<\/ol>\n

    In ChatGPT Makes GIGO Obsolete<\/a>, I’d posited that ChatGPT sources missing \/ erroneous data from third party data brokers. Advanced insights confirms that.<\/p>\n

    Some of these insights are FYI whereas others are actionable.<\/p>\n

    In this blog post, I’ll cover the actionable insights.<\/p>\n

    \"\"<\/a><\/p>\n

    Let’s get on with it.<\/p>\n

    1. Housekeeping<\/strong><\/p>\n

    While verifying the overall summary<\/em> (insight #3), I discovered inconsistencies in the rating descriptors across different rows e.g. Some 3* ratings were labeled “Good: Definitely worth reading”<\/em> whereas others said “Good: Worth reading”<\/em>. Ergo the following:<\/p>\n

    Actionable Insight<\/em>: Standardize the description of ratings.<\/p><\/blockquote>\n

    I did this manually by replacing the wrong descriptions in the source Google Sheet with the right ones. In hindsight, I realize that I could’ve written a prompt to have ChatGPT do the heavy lifting and saved myself a half hour or so of manual work.<\/p>\n

    2. Data Cleansing<\/strong><\/p>\n

    \"\"<\/a>In the overall summary<\/em> (insight #3), ChatGPT reported a mismatch between the counts of total books<\/em> (583) and unique books<\/em> (571).<\/p>\n

    This suggested that there were 12 duplicate entries (583-571). Ergo the following:<\/p>\n

    Actionable Insight<\/em>: Remove duplicates.<\/p><\/blockquote>\n

    To help me in this pursuit, I asked ChatGPT to list the duplicates and point out the rows in which they’d occurred. I reviewed its response and found that:<\/p>\n

      \n
    1. All of its duplicate calls were right.<\/li>\n
    2. Some row calls were also right e.g. “463 & 464, FROZEN PAST, Richard Hale”<\/em>.<\/li>\n
    3. Some row calls were offset by a few rows e.g. ChatGPT called “EXECUTIVE POWER, Vince Flynn”<\/em> on Row 33 and 38 whereas the duplication was actually in Row 35 and 40.<\/li>\n<\/ol>\n

      I de-duped these books in the original Google Sheets manually.<\/p>\n

      I then realized that some of the duplicates were not really duplicates e.g:<\/p>\n