DataHour: Anomaly Detection in Time Series Data

DataHour Recording

About the DataHour:

From manufacturing processes over finance applications to healthcare monitoring, detecting anomalies is an important task in every industry. There has been a lot of research on the automatic detection of anomalous patterns in time series, as they are large and exhibit complex patterns. These techniques help to identify the varying consumer behavior patterns, detect device malfunctions sensor data, monitor resource usage, video surveillance, health monitoring, etc. 

In this DataHour, Parika will talk about the different techniques used to identify both Point and Subsequence Anomalies in time series data. She will also cover both the statistical and the predictive approaches including CART models, ARIMA (Facebook Prophet), unsupervised Clustering and many more.

Prerequisites: A basic understanding of Python programming language and Time Series Data would be beneficial.

Who is this DataHour for?

• Students & Freshers who want to build a career in the Data-tech domain.
• Working professionals who want to transition to the Data-tech domain.
• Data science professionals who want to accelerate their career growth

Speaker:

Parika Vyas

Advanced Data Science Associate Consultant at ZS Associates

Parika works as an Advanced Data Science Associate Consultant at ZS Associates. She has 3 years of work experience at ZS and holds a B.Tech degree in Electronics & Communication Engineering from BIT Mesra. Parika specializes in providing Personalization & Marketing Data Science solutions to various industries from consumer health to pharmaceutical. She has worked with these clients for customer market segmentation, item recommendation, offer forecasting, AB Testing and more. Apart from all these technical proficiencies, she also enjoys exploring new state-of-the-art developments in the world of Artificial Intelligence.

Connect with her on Linkedin.