Search
Close this search box.

Tableau and the Intelligent Experience: Tools for Efficient ML Model Development

Tableau is an important tool in the Salesforce.com ecosystem that allows businesses to easily explore their data and highlight trends using powerful visualization tools. By building data visualizations and dashboards that can be embedded into web pages and reports, as well as Salesforce, organizations can create a seamless intelligent experience that integrates business strategy with AI and machine learning solutions. Tableau offers a way to bring these domains together by allowing individual users to explore data on their own as well as empowering teams to build reports/visualizations that can be deployed at production scale.

With machine learning solutions it can be difficult to surface model insights to the right people and efficiently drive change based on those insights. But with Tableau, users can easily surface analytics based on the data and pair model results and predictions with visualizations that further illuminate patterns seen by the machine learning model.

Machine learning algorithms are black box processes for a typical business user. Understanding how and why an algorithm is making a recommendation is important in developing trust in and taking the best action from the model. The construction, interpretation, and overall use of a machine learning model cannot be separated from the analytics that help us understand the data. Through descriptive statistics and visualizations built in supporting dashboards, we can understand how possible features in the model are related to each other and the outcome we’re trying to predict, as well as calculate and plot descriptive statistics for each variable.

An in-depth exploratory data analysis (EDA) is paramount to developing an effective machine learning solution. Through the use of Tableau, the development of a machine learning model can be achieved by:

  • Identifying patterns in missing data
  • Allowing investigations into quantity and quality of data
  • Giving insight into which features should be used in a training data set
  • Aiding in feature engineering choices
  • Helping to check model assumptions to make sure that we have appropriate data given the model choice and overall business goal

And through the creation of calculated fields and charts, Tableau is a powerful tool for conducting an EDA. With the ability to drag and drop fields into a Tableau sheet, we can quickly investigate the relationship between the outcome we want to model and features that might be related to it. Some example questions that we might ask include: Are there differences in won and lost opportunities based on amount, business segment, and type? Are certain fields left blank more often on lost opportunities? These types of questions provide insights into our data that guide the model development and action framework definition processes.

Once we have created dashboards supporting model choices and predictions are made using current data, these predictions can be brought into Tableau to gain further insight into model results. Tableau offers extensions to both R and Python that allows users to call out to model scripts, automatically score records, and save those predictions. Currently, predictions made in Einstein Discovery can be imported into Tableau as a data column and used to build charts and dashboards around model results.

If our machine learning model is inferential in nature and allows for interpretability of process drivers on the outcome of interest, it is extremely valuable to create charts that highlight the predictions of the model against the most important features in order to understand the differences that might be driving model results. For instance, if ‘# of In Person Meetings’ or ‘Deal Velocity’ are key features in an opportunity’s likeliness to close, it is important that users are able to visualize those measures and explore where they may be having a negative impact on pipeline health. Tableau dashboards with embedded predictions and insights around them can be used to help business owners easily digest the model results and validate the findings given their business and domain expertise. Tableau, in this way, can help in the process of model iteration as data scientists and strategy consultants work with business stakeholders to make sure that assumptions made through model development align with their business process.

As you can see, Tableau is a dynamic, robust tool that can be leveraged when implementing machine learning solutions for a business, as it provides the ability to quickly and efficiently explore data and aids in crucial model development choices, as well as provides an engaging and streamlined way to display model results for business stakeholders.

Related Content