Improving your model's accuracy
In Chapter 10, Training and Evaluating a Model, you trained an anomaly detection model and visualized the outputs over an evaluation period. Depending on what your business objectives are, here are several areas you may want to improve the obtained results:
- Too many false positives: After evaluating the events triggered by Amazon Lookout for Equipment against reality, you might see some events as false positives you would like to discard.
- Too many false negatives: In some cases, you might know about some anomalous events that were not detected in the evaluation period.
- No or too short forewarning time: Sometimes, anomalies are detected but too late and you want to get a longer forewarning time so that your end users have enough time to take the appropriate mitigation actions.
Reducing the occurrences of these situations will increase the trust your end user puts in the insights provided by the service and increase the added...