Announcing Syntasa 5.0: A New Kind of Technology for Digital Professionals

New year, new product release! As we gear up for 2020, we’re excited to announce the launch of Syntasa 5.0. We’ve considered a lot of user feedback as we work to build the best-ever version of our product. Everything in this release is designed to make it easier and simpler for you to use and find value in Syntasa.

So what’s new? Here’s a quick rundown.

• AppFlow Diagrams: One of our most requested features was the ability to get a high-level overview of all adapters, apps, models, and activation channels across an organization. AppFlow Diagrams do that and more. From the high-level flow view you can drill-down into each individual app, and see any dependencies on other apps.
• Product Assistant: With our improved product assistant, you’ll get feedback earlier and more often as you’re using Syntasa. This real-time feedback helps avoid common mistakes and saves time by alerting you if you’re creating a process that might produce unexpected results.
• Updated Look and Feel: We’ve done some redecorating to streamline and improve your user experience. We redesigned our navigation to help you keep track of where you are in the app at any given time. Menus are now grouped together more logically to make it easier for you to find exactly what you need. You can also favorite apps so that they’re always front and center in your interface, and even add custom icons to really make them your own.
• Interactive Mode: Our new interactive mode combines the real-time feedback of an interactive notebook with the reliability of a canvas. Set up your data and cluster and you’re good to go. Get results faster and prevent mistakes from compounding down the line, all while building in a production-ready environment.
• New Help Center: We’ve created a new help center that centralizes support, documentation, and community in one place at help.syntasa.com (login required). It’s the place where you’ll find helpful articles, release notes, and a new streamlined experience to make it easier to find guidance.

New Features

In addition to these quality-of-life improvements, we’ve also released several new features based on user feedback. These include:

Integrations:

• AAM API Adaptor: sends signals to specified traits in Adobe Audience Manager.
• AAM CDF Loader loads comprehensive Customer Data Feed files from Adobe Audience Manager and stores in your big data environment.
• Google Analytics Audiences Adaptor generates Audiences in Google Analytics.
• Adobe Analytics Reporting API runs a report in Adobe Analytics, extracts the report results, and stories it in your big data environment.
• Google Analytics Reporting API runs a report in Google Analytics, extracts the report results, and stores it in your big data environment.
• Adobe Classification API loads data used for SAINT classification rules in Adobe Analytics.

Data Science:

• Audience Quantile Selector selects the top X% of audience scored by a model.
• Quantile Evaluator evaluates model performance using business metrics and provides percentile statistics on a model’s predictions
• Feature Explorator automatically scans the feature space, runs several statistical tests, and identifies the most useful features
• Sample: under-sample, over-sample, or generate a random sample from a dataset; supports SMOTE to handle highly unbalanced classes
• Detrend (Seasonality Forecasting) removes seasonality-based noise in metrics used in forecasting

Under the Hood

We’ve also made several improvements to the more technical aspects of our product to keep things humming smoothly. These include:

• Feature Learn and Feature Transform: These new processes allow for automated feature generation and feature extraction within the platform. As you ingest new digital and customer data, it is automatically transformed into features, which you can use to build and evaluate models for a variety of business use cases. These features are kept in a Feature Store where anyone from data scientists to data analysts can use them to create, evaluate, and select new models.
• User-Defined Process: This feature is all about collaboration. With the introduction of user-defined processes, any advanced user (i.e., anyone capable of coding) can build a process that other members of your team can use in a code-free environment. For example, a data scientist might build the capability to perform a statistical test on a campaign that analysts can use independently. Or a data engineer can build a script to imports a CSV file that an analyst can use as they receive regular updated new files.
• Multi-Pipeline Orchestration: One of our most highly requested features, our advanced pipeline orchestration provides the ability to coordinate execution between multiple pipelines based on a number of factors including time as well as the completion or failure of specific previous steps.
  

You can read the full release notes for Syntasa 5.0 here. 

Ready to try out 5.0 today? Start your free trial today.