2021 / Personal Project / Kaggle Machine Learning & Data Science Survey Competition
Citizen Data Scientists: The role of Auto ML tools
This project aimed to explore and visualize the 2021 Kaggle Machine Learning & Data Science Survey. We decided to focus on how Automated Machine Learning is linked to the growing presence in the business of Citizen Data Scientists, a new professional figure.
Automated Machine Learning
Automated Machine Learning is automating the time-consuming, iterative tasks of the machine learning model development. As shown in the visualization below, the aim is to automate one or more phases of the classic machine learning pipeline, making it easier for non-experts to create machine learning models or allowing expert users to build models quicker and more efficiently.
Tableau Dashboards
What is the most effective way of communicating information? The correct answer to this question is it depends. It depends on the purpose of the project and the target audience. It depends on the level of detail one wants to reach, the visualization channel, and the tool used. It depends on many other variables.
For us, delivering a message by telling a story was the most important. Based on the message we wanted to convey, creating a traditional notebook was not the best choice. Instead, we enjoyed our visual project to be interactive, eye-catching, and strongly distinguished on a graphic level. For this reason, we have decided to display the CVs of our Personas, recalling the desktop-file interaction that anyone among us is familiar with. The metaphor used is relevant to the topic of our analysis (we are talking about how the working landscape in data science will transform) and to the type of data displayed (education, work experience, tools, skills, etc.).
For us, delivering a message by telling a story was the most important. Based on the message we wanted to convey, creating a traditional notebook was not the best choice. Instead, we enjoyed our visual project to be interactive, eye-catching, and strongly distinguished on a graphic level. For this reason, we have decided to display the CVs of our Personas, recalling the desktop-file interaction that anyone among us is familiar with. The metaphor used is relevant to the topic of our analysis (we are talking about how the working landscape in data science will transform) and to the type of data displayed (education, work experience, tools, skills, etc.).
The story creation and the dashboard design derive from a careful exploratory analysis of the dataset. This took place thanks to a simple heatmap that maps the Personas and the answers to the different questions.
The process
Unfortunately, Tableau is not a layout program; for this reason, we encountered many difficulties. Nevertheless, the final result came after multiple tests: the added value was undoubtedly brought by the continuous exchange of feedback, demonstrating that teamwork is always enriching.
Team With: Jacopo Repossi
