Analytics Platform Capabilities Explorer

AI and ML

Oracle Analytics embeds AI/ML throughout the platform, catering to users of all skill levels, from clickers to coders. Expand beyond built-in AI/ML capabilities with Oracle Database Machine Learning and OCI AI Services to cover a broader range of use cases.

Artificial intelligence and machine learning for analytics

Oracle Analytics embeds artificial intelligence, generative AI, and machine learning into every aspect of the analytics process, from data-to-decision, to improve user productivity and deliver better analytics-driven insights to support every role. Expand on built-in capabilities with additional Oracle Cloud Infrastructure (OCI) services to address even more AI/ML use cases.

Watch a one-click forecasting demo (1:18)

Machine learning for business users

Use one-click advanced analytics to display quick forecasts, trend lines, clusters, and reference lines. Users can customize the prediction interval and model type of the built-in algorithms to better fit the data and business use case.

Figure 1: Adding a forecast with one-click

With only a few clicks and no coding, you can use the Explain capability to examine the data set and identify meaningful business drivers, contextual insights, and data anomalies. Choose visuals and findings from Explain to start a new dashboard and story.

Figure 2: Automatically generate analytics-driven visual insights


The Auto Insights capability examines data sets and uses ML to automatically create visual insights with all the available metrics and attributes. This can reveal undiscovered connections and patterns in the data that may otherwise not have been considered. With one click, Oracle Analytics will display a range of visualizations with detailed descriptions that you can easily add to your project canvas. All the calculations used to derive the insights are transparent and editable.

Figure 3: Explaining metrics or attributes with one click


Use the Explain and Auto Insights capabilities to start your projects with ML-powered, analytics-driven insights and avoid blank canvas syndrome and biased outcomes.

Watch an NLP demo (1:16)

Natural language

Use AI-powered natural language processing (NLP) and natural language generation (NLG) along with generative AI–created responses to better interact with and understand the analytics. Simply use natural language—spoken or search keywords—to query any information from Oracle Analytics data sets and the semantic layer, without needing to understand where the data resides or the composition of the data set. Automatically render visualizations in context as the query is being built.

Figure 4: Natural language querying

NLG creates smart textual narratives of visualizations that, by default, are connected live to the data source and interact with other data objects on the canvas, such as visualizations and filters. The narrative detail has seven selectable levels, and the description can be set to either “trend” or “breakdown.” Textual narratives are available in multiple languages. Using the mobile app, you can convert analytics workbooks into spoken narratives, such as podcasts.

Figure 5: Natural language generation


Machine learning for data scientists

During data preparation, you can use the data flow editor to train numeric prediction, multi-classifier, binary classifier, or clustering models using different built-in algorithms. These ML algorithms can be customized, trained, tuned, and then published to the wider analytics user community. Once models are published, they can be applied to new corporate or personal data sets.

Figure 6: Customizing a linear regression ML mode

Models trained within Oracle Analytics Cloud can be checked for quality and accuracy. For example, this Naïve Bayes binary classifier has been trained with attrition data, and the quality of the algorithm is rated against the known true values from the test data.

Figure 7: Reviewing an ML model’s accuracy

Expanding with Oracle Database ML

Access the depth and sophistication of Machine Learning in Oracle Database, part of Oracle Autonomous Database. Machine Learning in Oracle Database provides a centrally governed platform to develop, test, and publish ML models using SQL, R, Python, REST, and AutoML. It gives business users the flexibility of using self-service approaches when preparing their data. Published models can then be registered into Oracle Analytics Cloud for wider business populations to access and execute with their own data sets.

You can use the AutoML capability in Oracle Database within an Oracle Analytics Cloud data flow. It will analyze your data set, automatically select the most accurate ML algorithm, and create a new ML model. This simplifies the process, allowing users to create accurate models without machine learning expertise.

Expanding with OCI AI Services

Oracle Analytics Cloud integrates with OCI AI Services, including OCI Vision and OCI Document Understanding. These integrations extend Oracle Analytics Cloud’s existing embedded machine learning capabilities to support an even broader range of business use cases. Use pretrained models or design, refine, and deploy custom models, and register them within Oracle Analytics Cloud so business professionals can access them directly.

OCI Vision brings the power of AI image analysis to Oracle Analytics Cloud dashboards. Imagine using data from security cameras to automatically track car park occupancy or monitor customer foot traffic in stores. OCI Vision analyzes images and translates the visual information into insights, allowing businesspeople to tell data stories based on what can be seen.

With OCI Document Understanding, you can apply AI models to documents—such as JPEG and PDF files—and extract key values and their context. This helps you unlock information from documents to generate additional insights, even if the information hasn’t been recorded in a central database.


These dynamic, self-service approaches reduce business users’ reliance on your data science team for routine, repetitive model execution and results delivery. Business users can independently schedule and execute their models, enabling data science experts to focus on more strategic tasks.