Join Informatica for this four-part series, to hear how industry-leading companies leverage Artificial Intelligence and Machine Learning best practices to develop and train their Data Science Models.
Below you will find the list of dates and stages that we will feature. Each session will be recorded and recordings of previous sessions will be provided after your registration. Register once to participate in all of the series sessions.
Discovery – November 3
Learn the first stage to Discover the enterprise data you will need for an effective Data Science Model. We will review how to find the data (known and unknown) and assign asset scores and tags to various data assets.
Data Collection – November 10
Now that we determined the assets required, we need to get it to the right modeling team using a JIT (just in time) automated process. These data assets include operational systems, JSON, Avro, Parquet, SaaS API-based applications, and Cloud-native S3, ADLS Gen2, Snowflake, Redshift, SQL Data Warehouse, BigQuery, etc. During this session, we will discuss various collection methods.
Exploratory Data Analysis – November 17
This is pre-Modeling and is used to develop and to train your Models. This session will discuss Feature Selection, Feature Engineering, and Data Processing/Wrangling needed to categorize, detect anomalies, standardize, detect variances, and prepare for Model agnostic use.
Training and Data Engineering – December 1
This is post-Modeling and is used to test your Models. During this session, we will discuss API Management and the deployment and visualization of Model results to train and deploy your Data Science Data Models for enterprise use.