top of page

Automation using AI and ML in Oracle Analytics Cloud (OAC)

Oracle Analytics Cloud (OAC) stands as a powerful and comprehensive analytics solution, purpose-built to empower organisations in their journey towards data-driven decision-making. With its robust suite of features and cutting-edge capabilities, OAC revolutionises the way businesses analyse, visualise, and derive insights from their data.

In this article, am going to specifically explore a few key capabilities of OAC around the automation of repeated tasks using its integrated AI and ML features.


Data Preparation

By harnessing ML algorithms, Oracle Analytics Cloud empowers organisations to streamline data preparation processes, significantly reducing manual intervention and accelerating time to insights. This assertive approach ensures data quality, reliability, and precision, laying the foundation for impactful decision-making and driving organisational success. Let us take a glance at how.

Data Preparation in OAC

Data Profiling

OAC's ML algorithms meticulously analyse dataset characteristics, swiftly detecting

anomalies, outliers, and inconsistencies. Through advanced pattern recognition, OAC

identifies data types, distributions, and unique values, laying the groundwork for precise


ML algorithms in OAC analyse the characteristics and distribution of data within datasets automatically. This includes identifying data types, data ranges, and unique value counts for each column.

  • Through pattern recognition and statistical analysis, ML algorithms can detect anomalies and irregularities in the data, such as unexpected data distributions or values that deviate significantly from the norm.

  • OAC may also utilise unsupervised ML techniques, such as clustering algorithms, to group similar data based on patterns and similarities, facilitating the identification of data segments with common attributes.

Data Cleansing

With ML-powered intelligence, OAC promptly identifies and rectifies potential data inconsistencies. Leveraging supervised ML techniques, it learns from historical data and user feedback to autonomously cleanse and standardise data with unmatched precision.

  • ML algorithms in OAC can automatically identify and flag potential data inconsistencies, such as duplicate records, conflicting values, or formatting errors.

  • OAC may employ supervised ML algorithms to learn from historical data and user feedback, allowing it to make intelligent decisions about how to cleanse and standardise data automatically.

Missing Value Imputation

OAC predicts and fills in missing values seamlessly by leveraging ML algorithms to discern intricate data relationships. Supervised methods, including regression and decision trees, enable OAC to accurately predict missing values, ensuring data completeness and integrity.

  • OAC can leverage ML algorithms to predict and impute missing values within datasets based on the relationships and patterns observed in the data.

  • Supervised ML techniques, such as regression or decision trees, may be used to predict missing values by analysing the relationships between other variables in the dataset.

Outlier Detection and Handling

OAC's ML algorithms possess the prowess to identify outliers, leveraging supervised and unsupervised techniques to distinguish between normal and anomalous data points. With precision, it flags outliers, ensuring data quality and reliability for insightful analysis.

  • ML algorithms in OAC can automatically identify outliers within datasets by analysing data distributions, statistical measures, and patterns.

  • Supervised outlier detection algorithms may learn from labelled data to distinguish between normal and anomalous data points, allowing OAC to flag outliers with high confidence.


Smart Data Visualisation

Use fancy AI tools to pick the best charts, colours, and visuals based on your data and what you're analysing. Also, make it talk by itself - automatically writing up descriptions explaining what you're seeing in your charts and data.

By combining the smart data visualisation capabilities curated below, Oracle Analytics Cloud empowers users to explore, analyse, and communicate insights effectively, enabling data-driven decision-making and driving business success.

Automatic Chart Recommendations

OAC's smart data visualisation feature automatically suggests the most suitable chart types based on the data attributes and the analysis context. By analysing the data's dimensions, measures, and relationships, OAC intelligently recommends charts that best represent the data and help users gain insights quickly.

Adaptive Color Schemes

OAC dynamically adjusts colour schemes based on the data being visualised and the analysis objectives. By considering factors such as data distribution, trends, and categorical values, OAC ensures that the colour palette enhances the readability and clarity of visualisations, making it easier for users to interpret the data.

Interactive Visualisations

OAC offers interactive visualisation capabilities that enable users to explore and interact with data dynamically. Users can drill down into data, apply filters, and change visualisation parameters in real-time to gain deeper insights and discover hidden patterns within the data.

Integrated Analytics

OAC seamlessly integrates advanced analytics capabilities, such as machine learning algorithms and statistical functions, directly into visualisations. This integration allows users to perform complex analyses and predictive modeling within the context of their visualisations, enabling to derive actionable insights more efficiently.

Natural Language Generation (NLG)

OAC incorporates NLG capabilities to automatically generate textual descriptions and narratives explaining the insights and trends observed in visualisations. By leveraging NLG, OAC enhances the interpretability of visualisations and enables users to communicate findings effectively.


Insights Generation

Oracle Analytics Cloud (OAC) offers several features and capabilities to automate insights generation, empowering users to uncover valuable insights from their data efficiently. Here's how!

Auto Insights

Auto Insights is focused on automatically analysing datasets and identifying significant trends, patterns, and outliers without requiring manual exploration. Users can enable Auto Insights for their datasets or analyses, and OAC will autonomously generate actionable insights based on the data. These insights may include key trends, correlations, anomalies, and other noteworthy observations.

Auto Insights is particularly useful for users who want to quickly gain insights from their data without performing extensive analysis manually. It helps users uncover hidden insights and trends that may not be immediately apparent through manual exploration.


Explain is designed to provide users with contextual explanations and insights into their data visualisations and analysis results. Users can access the Explain feature to delve deeper into specific data visualisations or insights generated within OAC. Explain provides detailed explanations of the underlying data patterns, statistical significance, contributing factors, and potential implications.

Unlike Auto Insights, which focuses on automating insights generation, Explain helps users interpret and understand the insights and findings derived from their data. It provides users with the context and background information needed to make informed decisions based on the analysis results.

Explain is valuable for users who want to understand why certain trends or patterns are present in their data, what factors are influencing specific outcomes, and what actions they should take based on the analysis findings. It facilitates a deeper understanding and interpretation of analysis results.

In summary, while both Auto Insights and Explain features in Oracle Analytics Cloud aim to provide insights from data, Auto Insights automates the process of insights generation, while Explain offers contextual explanations and insights into analysis results. They complement each other by providing users with both automated insights and detailed explanations to support informed decision-making.


Automated Report Generation

Oracle Analytics Cloud (OAC) streamlines the process of report generation through automation, enabling users to create and distribute reports efficiently. Here's how OAC achieves automated report generation:

Drag-and-Drop Interface: OAC's intuitive drag-and-drop interface allows users to easily add data visualisations, tables, and other elements to report templates.

Scheduled Reporting: OAC allows users to schedule report generation and distribution at predefined intervals, such as daily, weekly, or monthly. Users can specify recipients, delivery methods (e.g., email, file storage), and report formats (e.g., PDF, Excel) for scheduled reports, ensuring that stakeholders receive timely and relevant information.

Automated Data Refresh: OAC automatically refreshes data in reports based on predefined schedules or triggers. Users can configure data refresh settings to ensure that reports always reflect the latest information, reducing the need for manual data updates and ensuring data accuracy.

If you would like to understand more details about automated data refresh - you can refer it in the detailed article I have written in Rittman Mead Blogs.

By leveraging these automation capabilities, Oracle Analytics Cloud enables users to generate reports quickly and efficiently, ensuring that stakeholders have access to timely and actionable insights to support informed decision-making.

Automating repetitive tasks using AI and ML in Oracle Analytics Cloud (OAC) can significantly improve efficiency and productivity. Hope the discussed features were helpful in some way to automate repetitive tasks that you come across, accelerate decision-making, and unlock actionable insights from data more efficiently and effectively.

94 views0 comments


bottom of page