Remove tag domain-modeling
article thumbnail

Machine Learning for Fraud Detection in Streaming Services

The Netflix TechBlog

We present a systematic overview of the unexpected streaming behaviors together with a set of model-based and data-driven anomaly detection strategies to identify them. There are two main anomaly detection approaches, namely, (i) rule-based, and (ii) model-based.

C++ 312
article thumbnail

Dynatrace extends contextual analytics and AIOps for open observability

Dynatrace

Relying solely on traditional analysis methods like tagging and data correlation to answer such questions is inadequate when an IT landscape isn’t properly represented in a data model or when the cause-and-effect chain of services remains unclear.

Analytics 246
Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

Detecting Speech and Music in Audio Content

The Netflix TechBlog

Music information retrieval There are a few studio use cases where music activity metadata is important, including quality-control (QC) and at-scale multimedia content analysis and tagging. The best model was a CRNN with three convolutional layers, followed by two bi-directional recurrent layers and one fully connected layer.

article thumbnail

Scalable Annotation Service?—?Marken

The Netflix TechBlog

Scalable Annotation Service — Marken by Varun Sekhri , Meenakshi Jindal Introduction At Netflix, we have hundreds of micro services each with its own data models or entities. Annotations Sometimes people describe annotations as tags but that is a limited definition. Teams should be able to define their data model for annotation.

article thumbnail

Open-Sourcing a Monitoring GUI for Metaflow

The Netflix TechBlog

Following our culture of freedom and responsibility , Metaflow grants data scientists the freedom to choose the right modeling approach, handle data and features flexibly, and construct workflows easily while ensuring that the resulting project executes responsibly and robustly on the production infrastructure.

article thumbnail

Connect Fluentd logs with Dynatrace traces, metrics, and topology data to enhance Kubernetes observability

Dynatrace

Processing plugins parse (normalize), filter, enrich (tagging), format, and buffer log streams. Moreover, domain knowledge is required to sift through the vast amount of disconnected log files and find the proverbial needle in the haystack. Fluentd can run as a DaemonSet in a Kubernetes cluster.

Metrics 176
article thumbnail

Connect Fluentd logs with Dynatrace traces, metrics, and topology data to enhance Kubernetes observability

Dynatrace

Processing plugins parse (normalize), filter, enrich (tagging), format, and buffer log streams. Moreover, domain knowledge is required to sift through the vast amount of disconnected log files and find the proverbial needle in the haystack. Fluentd can run as a DaemonSet in a Kubernetes cluster.

Metrics 130