Our Agile & CRISP-DM based
“Meta” Methodology

Modeling Phase​​

• Launch a Strategy Workshop

​

• Ask core questions to uncover your unique needs

​

• Conduct resource recognition to match our capabilities with your needs 

​

• Establish support, trust, and motivation with your data teams

• Understand details about data infrastructure & our toolset alignment

​

• Extract data

​

• Preprocess and parse the data as needed

​

• Prioritize transparency by providing ongoing education

• Use our arsenal of algorithms & softwares to create preliminary models 

​

• Run thousands of experiments in parallel

​

• Engineer features and tune hyperparameters to improve model accuracy

​

• Select the model that is most likely to succeed

• Collaborate with key stakeholders and technical partners

​

• Focus on assessment & feedback of preliminary models

​

• Return back to the preparation and modeling phase with the feedback

​

• Continue iterative process until key stakeholders are satisfied

• Provide models and/or final recommendations from models

​

• Integrate the model with APIs or front-end applications

​

• Maintain and update the model/application as needed