Anomaly Detection

OCI Anomaly Detection is an AI service that provides real-time and batch anomaly detection for univariate and multivariate time series data. Through a simple user interface, organizations can create and train models to detect anomalies and identify unusual behavior, changes in trends, outliers, and more.

Anomaly detection features

Proprietary anomaly detection algorithms

OCI Anomaly Detection algorithms, backed by more than 150 patents, detect anomalies earlier with fewer false alarms. These algorithms work together to ensure higher sensitivity and better false alarm avoidance than other machine learning (ML) approaches, such as neural nets and support vector machines.

Blog: The fascinating (nuclear) history behind Oracle’s new anomaly detection service

Intelligent data preprocessing

OCI Anomaly Detection provides multiple data processing techniques that account for errors and imperfections in real-world input data, such as from low-resolution sensors. It automatically identifies and fixes data quality issues—resulting in fewer false alarms, better operations, and more accurate results.

Custom-trained models

APIs help developers upload raw data, train the anomaly detection model using their own business-specific data, and detect anomalies from the stored model. This makes creating highly accurate, custom-trained anomaly detection models accessible to everyone—even without data science experience.

Open-source options

Easy access to open-source technologies expands usage of OCI Anomaly Detection’s models. Pull time-series data from InfluxDB or streaming data from Apache Flink. Use open-source libraries like Plotly, Bokeh, and Altair for visualizations and to increase automation.

Ready-to-go results

OCI Anomaly Detection outputs include identified anomalies, ML model-based estimated values, and anomaly scores. Developers use these results to assess the severity of identified anomalies and automate business workflows to address them immediately.

Easy to integrate and deploy

OCI Anomaly Detection is a multitenant service over public REST APIs. Developers can deploy a scalable anomaly detection service easily without in-house data science and ML support, all with the lowest cost platform for data networking, storage, and egress.

Scalability on demand

OCI Anomaly Detection automatically scales for training and detection needs across all data sources and loads. Developers can now focus on creating applications and solutions to achieve their business goals, without worrying about the infrastructure.

Read about our customers' success stories

Sports Technology
SailGP generates almost 400 million inferences per race with OCI Anomaly Detection
Transportation Logistics
Improving vehicle uptime and on-time cargo delivery

Anomaly detection use cases

  • IT operations use cases

    OCI Anomaly Detection helps IT teams improve service levels, root cause analysis, IoT deployments, threat reduction, and database transaction monitoring.

  • Business operations use cases

    From fraud detection for banks to funnel conversion for marketing teams, OCI Anomaly Detection enables organizations to discover issues and opportunities to improve their business processes’ innovation and efficiency.

  • AI and ML operations use cases

    OCI Anomaly Detection improves AI and ML processes, including apps monitoring, data cleansing, and data training. Use anomaly detection to discover unexpected changes in model accuracy, improve data integrity, and optimize model and application performance.

  • Finance and retail: Fraud detection

    Fraud patterns change over time, and traditional deep-learning methods don’t always detect rare events in very large data sources. Specialized algorithms can identify fraudulent transactions immediately—catching fraudsters in real time, with fewer false alarms, than other ML approaches.

  • Utilities: Energy management

    Utility companies must monitor energy production and consumption in real time to dynamically respond to demand and to optimize energy consumption. Innovative ML approaches analyze energy production, weather, and control-systems data to deliver an optimal experience for both energy producers and consumers

  • Manufacturing: Operational efficiency

    Anomaly detection of operational metrics in real time—such as yield, utilization, and throughput—can identify undesirable changes in production and generate automated workflows for immediate action.

  • Transportation and manufacturing: Equipment monitoring

    Breakdowns in equipment mean lost productivity and even risk to employees. Fast detection and root cause analysis for parts and machinery keep systems running smoothly.

July 13, 2021

Deploy remote diagnostics without in-house data science and ML experts

Viji Krishnamurthy, Senior Director Product Management, Oracle

OCI Anomaly Detection is a robust, scalable and user-friendly AI service that watches large volume multivariate time series data and alerts you when something warrants your attention. Authenticated users can access OCI Anomaly Detection Service—part of our public cloud offering—via REST API, command-line interface, development kit, or the Oracle Cloud Infrastructure console.

Related cloud products

OCI Data Science

Open source algorithms and frameworks

OCI Data Integration

Combine and transform data for data science and analytics

OCI Data Catalog

Find and govern data using an organized inventory across the enterprise

OCI Data Flow

Run Apache Spark applications on a fully managed big data service

Get started with Anomaly Detection

Perform a free build in OCI Anomaly Detection

Build an ML model in an OCI workshop. Detect production anomalies in just a few guided steps.

Contact sales

Chat live with sales or support.