Datadog is introducing a new artificial intelligence feature to provide better insight into cloud applications. The company announced Forecasts, a new feature designed to predict performance and stability issues before they happen.
Users can use Forecasts to visualize predicted trends as well as specify how far in advance they want to be alerted about potential issues.
“Today, DevOps teams often receive critical alerts after their customers have been negatively impacted,” said Brad Menezes, Datadog’s product manager for artificial intelligence and machine learning. “Our forecasting algorithms have been fine-tuned based on trillions of data points across hundreds of thousands of servers daily. We can predict where a metric will be in the future, taking into account historical patterns, and notify users with plenty of time to prevent any negative impact. This directly translates into dollars saved and better user experiences – something every organization needs.”
The forecasts will be able to account for fluctuations related to seasonality. The seasonal forecasting algorithm takes recurring patterns into account. Additional algorithms will also be able to analyze recent behavior to adjust predictions. For example, if someone frees up disk space by removing logs from the server, the forecast will account for that and adjust its prediction. In addition, the forecast algorithms can predict how likely it is that critical business metrics will change.
According to the company, adding forecasts to the dashboards will allow customers to combine historical trends with future predictions. This will allow them to add correlations to metrics, such as anomalous traffic to the web servers, forecasted API request traffic, and forecasts of disk usage on database servers.
“Combined with other machine learning–powered monitoring features like anomaly detection and outlier detection, forecasts can help you gain more insights into your metrics than ever before,” Datadog wrote in a post.