Free courses from frontend to fullstack and AI
Learn AI, Data Science & Business — Earn Certificates That Get You Hired
Overview
AI, Data Science & Cloud Certificates from Google, IBM & Meta — 40% Off
One plan covers every Professional Certificate on Coursera. 40% off Coursera Plus Annual.
Unlock All Certificates
Explore the capabilities of Large Language Models (LLMs) in detecting data anomalies in this 25-minute conference talk from Conf42 LLMs 2024. Delve into the importance of data quality, examine the various causes of poor data quality, and learn about different approaches to address these issues. Investigate the effectiveness of OpenAI's models in anomaly detection, and discover BigQuery's built-in anomaly detector. Gain insights into key code components, threshold adjustments, separate training data incorporation, and tuning non-seasonal order terms to enhance anomaly detection performance. Conclude with information on how to connect with the speaker for further discussion on this crucial aspect of data analysis and LLM applications.
Syllabus
intro
preamble
this is me
why data anomalies?
why is data quality so important?
bad quality has a long list of causes
what can we do about it?
how good is openai with anomalies?
bigquery has an in-built anomaly detector
lots of code but this is the key part
increase the threshold
adding separate training data
tuning non-seasonal order terms
get in touch
Taught by
Conf42