IT Support Data Analysis
Introduction:
This was a project for my IT Data Analyst position. The data is about IT support. The main point of this analysis was to explore and analyze the IT support data to identify any meaningful trends and patterns in things like type of support, date of support, status of the case, etc. This data consists of 1 worksheet which contains 7,600+ records.
Insights:
There were many important insights to uncover from analyzing this data:
-
What's the breakdown of units by month and day?
-
How many cases was each employee assigned?
-
When did most of the cases occur?
-
What's the count of cases for each state and task Type?
Tools:
This project was analyzed using Excel, SQL, Tableau, and Python:
-
Excel was used because it was requested by my supervisor. I started by creating a column called 'Unit Grouping?' to group the Assignment Group column into categories. I did this by using a nested IFS function. Then I created 7 pivot tables to answer key questions and compiled them in a dashboard on Excel.
-
SQL was used because I wanted to analyze the data further to derive more insights. I started by cleaning the worksheet which included changing column names, changing data types, and updating blank values. Then I outlined a total of 13 questions and wrote queries for each one. The clauses used included: SELECT, FROM, WHERE, GROUP BY, SUM, COUNT, HAVING, ORDER BY, LEFT JOIN.
-
Tableau was used because I wanted to visualize my analysis from the SQL queries and explore the data even more to identify trends and patterns not discovered using Excel and SQL. I started by importing the Excel worksheet. Then I created 3 worksheets with visuals comprised of bar graphs and line charts. One of these visuals used a parameter and calculated field to alternate between visuals; this was very useful because instead of creating 8 different bar graphs, the user could just use a drop-down menu to switch between these 8 visuals. Then I compiled these 3 worksheets into a dashboard.
-
Python was used because I wanted to analyze the data further using a different tool. The data was already cleaned, so I started analyzing it. I outlined a total of 12 questions and used Pandas to answer them and Matplotlib to visualize them. The main Pandas syntax used were groupby, sort_values, and date. The main Matplotlib visuals used were bar graphs and line charts.
Impact:
The impact from this analysis was it provided stakeholders with valuable insights to optimize operations and improve decision-making. For example, understanding the breakdown of cases by time and task type allowed for better resource allocation and prioritization, ensuring adequate support during peak periods and for critical issues. Additionally, insights into employee workload distribution could help balance assignments, reduce burnout and improve efficiency. Visualizations from Tableau and Python further enhanced stakeholder communication, enabling clear identification of trends and opportunities for proactive problem-solving. These insights collectively empower stakeholders to improve IT support processes, enhance user satisfaction, and drive continuous improvement initiatives.