April 2023 Summaries

Behavioral data, derived from interactions and actions of individuals or groups, is a potent resource for enhancing machine learning models, particularly in understanding and predicting customer behavior. Despite its potential, behavioral data is underutilized in machine learning due to complexities such as data scattering across multiple systems, challenges in ensuring accurate data lineage, and compliance issues related to privacy laws. An example from a Kaggle competition hosted by Airbnb illustrates how incorporating web sessions data can improve prediction accuracy by enriching the training data with behavioral features. The article highlights Snowplow, an enterprise Behavioral Data Platform, as a solution to simplify and automate the use of behavioral data in machine learning by providing a structured, comprehensive dataset while ensuring privacy compliance, thus making it viable for AI applications.

The AWS Security Bundle from Snowplow is an enhancement to the Snowplow BDP Enterprise that provides an extra layer of security for implementations on AWS. It includes several features such as VPC peering, allowing customers to integrate their VPC with the Snowplow VPC by choosing a specific CIDR/IP range, and custom tagging, offering up to five tags for AWS resources like VPC and S3 buckets. Customers can also install custom security agents on EC2 servers to meet specific compliance needs using S3 objects, and extend IAM policies for additional permissions required by these agents. The bundle offers control over SSH and HTTP access, permitting the disabling of SSH and non-encrypted HTTP traffic to align with internal security protocols. Additionally, customers can set IAM Permissions Boundary policies to define specific permissions for Snowplow services. This bundle enhances the already private and compliant Snowplow solution by allowing customers to deploy infrastructure in their own cloud environment and manage storage and tracking details effectively.

Safari's latest update, version 16.4, has introduced new limitations on server-set first-party cookies, capping their lifespan at seven days if the server setting the cookie resolves to a third-party host or has differing IP address segments from the website's server. This change affects users employing server-side tag managers and complicates tracking customer journeys on Safari, impacting analytics and marketing attributions. To counteract these limitations and maintain long-lasting identification cookies, solutions such as deploying a cloud CDN as a proxy server or using cloud-native load balancers are recommended. Snowplow also offers an ID service to address these challenges in complex environments, ensuring continued effectiveness in user tracking and data collection amid evolving browser restrictions.