Overview
Anomaly Detection is used to identify any unusual behaviour or pattern in a dataset, used in many applications like Fraud Detection in Banking Sector, Pattern Analysis of Network Traffic, Predictive Maintenance and Monitoring.
Our Approach offers AI-powered Log Analytics solutions for Anomaly Detection, finding a Correlation between Anomalies and Predicting Anomaly in the IT Infrastructure using Machine Learning and Deep Learning.
Business Challenge
-
Extensive usage of data growth on a daily basis with the evolution of technology.
-
Increased occurrence of unusual behaviour or fraud activities
-
Need for detection in a timely manner to perform maintenance and achieve monitoring effectively.
Solution Offered
-
Data Preprocessing
Dataset is loaded and stored in the object and datatype of the dataset is checked and converted into float values. After conversion, the total number of hours is calculated from date and time and converted dataset is loaded as a series.
-
Data Wrangling
Time series data is plotted and visualized. In order to get the values of AR, I and MA plotting of autocorrelation and description of residuals are necessary.
-
Model Implementation
ARIMA model is implemented and predicted values are obtained and forecast errors are calculated. Then mean and standard deviation of the dataset are calculated and anomalies are computed.