In “Is a Tesla in Your Future?” Part 1, Part 2, and Part 3, we explored what demographics, lifestyles, credit scores, friends, habits, locations, and reviews do the Tesla audience share? We take a deep and fun look at our current Tesla owners using demo data and Oracle Autonomous Database, Oracle Machine Learning, and Oracle Analytics Cloud.
Download the on-premises version presentation that uses Oracle Data Miner (click to download ODMr workflow) and Oracle Analytics Cloud.
In Part 1 we build and apply Oracle Machine Learning models inside Oracle Database to identify those people who are most likely to buy Teslas.
In Part 2, we repeated that process using Oracle Machine Learning AutoML UI.
In Part 3, we added 3 additional datatypes to create a more complete 360-degree customer POV:
– Tesla reviews (unstructured data)
– Tesla friends (relationship / “graph” data)
– Telsa location data (geospatial / transactional location data)
Now in our final Part 4, we interactively explore our OML insights and predictions using Oracle Analytics Cloud. Starting in release 5.6, OAC added the ability to register an Oracle Machine Learning model. Users have the option of either visualizing OML predictions and insights in Oracle Database tables or using OAC’s ability to register an OML model, add it to Data Flow, apply the OML to new data and interactively visualize the predictions and insights.
We use Oracle Analytics Cloud to select and register an OML model so it can viewed, explored and applied in OAC Data Flows.
OAC allows you to assign access to the model and inspect the model and model views.
We now can create an OAC Data Flow with our Tesla Buyers OML model to make predictions,
Once you have added Oracle Machine Learning’s predictions, models, and insights you can explore them interactively using Oracle Analytics Cloud and share the results with others throughout the enterprise.
Whereas Oracle Analytics Cloud 6.0 adds in-database analytics functionality users can run without using any code, in this instance, we previously run this text indexing script from SQL Developer (or SQLDEV web) to create the text index table we graph in our Tesla Review canvas
CREATE INDEX TOKEN_INDEX ON TESLA_REVIEWS89(REVIEWS) INDEXTYPE IS CTXSYS.CONTEXT;
Oracle’s “Converged” Database enables IT professionals, data analysts, data scientists, application developers, and domain experts to collaborate to deliver predictive solutions faster than other island and legacy architectures. Hope you found this “Is a Tesla in Your Future?” blog series was fun and informative and hope you have a new Tesla is in your future!
Download the fun Tesla Demo Artifacts (Tesla demo datasets TESLA_78, TESLA_REVIEWS89, TESLA_FRIENDS89, TESLA_LOCATIONS89, Is a Tesla in Your Future_ A 360-degree POV using OML OML notebook, and Tesla Buyers OAC Project.dva)
– Naman Mehta Principal Member of Technical Staff who worked diligently to get all the complex SQL joins, text mining components to work and for his passion and help to create this fun and educational demo scenario.
– Philippe Lions, Senior Director, Product Management, Analytics Platform, Oracle Analytics Cloud (OAC) for his expertise, ideas, and help in highlighting OML working with Oracle Analytics Cloud.
– Siddesh Chikkanayakanahalli Prabhu Dev Ujjni, Staff Cloud Engineer for his dedication, hard work, knowledge, and help in creating this and other OML demo scenarios.