“Is a Tesla in Your Future?” Part 2 – Let’s do that again using OML AutoML UI

In Part 1, we explored what demographics, lifestyles, and habits do the Tesla audience share? We started by using historical data about current Tesla buyers using Oracle Analytics Cloud and built, evaluated, and applied Oracle Machine Learning models to identify individuals most likely to buy Tesla cars. We used OML’s notebooks.   This time will repeat that machine learning process using Oracle Machine Learning AutoML UI.

1. First, let’s look at our Tesla customer data using OAC, ADW, and OML Notebooks

  2. Let’s do that again with OML AutoML UI

  3. Now, let’s add 3 different data types 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)
  
  4. We build, evaluate, and apply OML models on this 360-degree customer data to target people likely to buy a Tesla

  5. Finally, we import OML models into Oracle Analytics Cloud, create a Data Flow, and interactively analyze our prospects

 

 

Oracle Machine Learning AutoML UI provides a powerful and easy-to-use UI for Citizen Data Scientists, Data Scientists, and Developers. OML UI automates model building, tuning, and deployment and enhances data scientist productivity.  Using OML AutoML UI data professionals who are not ML experts can easily build ML models and collaborate with data scientists, application users, and data analysts using Oracle Analytics Cloud to refine the models and disseminate OML’s insights and predictions throughout the enterprise or within applications.

OML AutoML UI Experiment Pipeline delivers faster and easier machine learning for Citizen Data Scientists, Data Scientists & Developers


 

With just 6 clicks we can define and launch an OML AutoML Experiment to find our likely Tesla customers.   OML AutoML UI creates an ML pipeline that automates the many steps experienced data scientists often perform.


 

When OML AutoML finishes, we can select the model with the best model metrics (e.g. accuracy), understand the key attributes in the model, create OML notebooks to extend the model, and deploy the model via other OML notebooks, OML Services (REST endpoints) and Oracle Analytics Cloud.

OML Notebooks can be used to extend and deploy models using OML4Py, OML4SQL, and OML Services.   

Here, we take our selected “best” model generated using OML AutoML UI and use an OML Notebook to apply it to our prospective customers to generate our predictions.  We do this100% inside Oracle Database to provide scalability, eliminate data movement, preserve security and more easily disseminate our OML insights and predictions throughout the enterprise.

Additionally, OML models can be registered in Oracle Analytics Cloud and used in OAC Data Flows to apply OML models inside Oracle Databases.

Next, let’s add our unstructured Teslas reviews, spatial location data, and friend relationships (“graph”) data to gain a 360-degree customer view.   We will then use Oracle Machine Learning to build models that incorporate all this data next in Is a Tesla in Your Future? – Part 3 where we add 3 different data types to create a more complete 360-degree customer point of view (POV):|   
– Tesla reviews (unstructured data)   
– Tesla friends (relationship / “graph” data)
– Telsa location data (geospatial / transactional location data)

More on Oracle Analytics Cloud and Oracle Machine Learning integration (YouTube) in Is a Tesla in Your Future? – Part 4.   

Back to “Is aTesla in Your Future?”  A Machine Learning Approach using Structured, Unstructured, Relationship and Location Data – Part 1

See “Is a Tesla in Your Future? A Machine Learning Approach using Structured, Unstructured, Relationship and Location Data” presentation.

Download the on-premises version presentation that uses Oracle Data Miner (click to download ODMr workflow) and Oracle Analytics Cloud.

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)

Acknowledgments/Contributors: 
– CharlieDataMine@gmail.com
– 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.

 

 

 

 



Source link

Leave a Reply

Your email address will not be published.