This past April, we released V9 of the Aktana platform, and many of our customers are already taking advantage of the enhancements available.
With V9, we aimed to help our customers execute strategies that are even more effective, without introducing additional complexity. Improved rule-driven support now makes it easier to define strategies that call for conditional logic and specific impacts. At the same time, we made configuration setup more transparent, allowing greater visualization of the impact of data profiles and rules on the engine. New machine learning optimization modules, like our Email Message Sequence Module, have also been introduced to enable strategy optimization at the physician level without rule proliferation.
Easier Setup of Sophisticated Rule-Driven Configurations
With V9, it’s much easier to set up and maintain use cases that require complex, rule-driven configurations, including conditional strategies, micro-segmentation and more.
- Setup is streamlined with better native support for creating rules that use sophisticated conditional logic.
- The impact of a rule on the priority of suggestions can be defined with greater precision, unlocking more powerful use cases and reducing the need for workarounds.
- Configurations can be edited and reprioritized more quickly based on changing business strategies, reducing time and risk between configuration iterations.
From Test-and-Learn to Fine-Tune
V9’s transparent configuration helps you understand the impact of data and rules on suggestions and insight output – even when your strategies are highly sophisticated. New tools make it easy to:
- Understand the data profile behind the critical data points driving your configuration.
- Analyze and visualize how the data points are playing out with your current configuration settings.
- Edit and refine the thresholds to see the impact of your changes immediately.
Make Rep Relationships Stronger Than Ever
Creating smarter Suggestions continues to be a focus in V9, with even greater emphasis on context. For example, Aktana’s engine is able to consider the strength of the relationship with the HCP when deciding which rep should receive a suggestion for a shared account and territory.
- Historical interactions between reps and HCPs can be synthesized to assess rep-account affinity.
- Parameters can be configured to consider factors like recent channels and interactions to ensure that suggestions continue to “feel right” to the rep.
- Rep-account affinities can be considered and weighted in relation to other elements of strategy.
Optimizing Email Messages
V9 moves beyond the execution of strategy to help customers answer the question, “what email message should we deliver next to HCPs?” While customers have always been able to design strategies for specific HCP segments, the new Email Message Sequence Optimization Module uses machine learning to identify optimized email sequences for each HCP, allowing Marketing to decide how these learnings should be integrated into the engine.
- Optimized email message sequences for each HCP are identified based on historical messages and responses and updated in real time.
- Marketing can configure which attributes and features the machine learning model should consider and what the target is (e.g., open or clickthrough rates).
- Marketing can configure how learned sequences should be integrated back into the engine and can choose to leverage optimal sequences for specific sub-segments only, or with defined constraints.