Elder Research uses the Analytics Prototype service to conduct an exploratory analysis using Agile methodology to demonstrate whether predictive analytic techniques can be used to answer an important business question and/or improve a current modeling effort.
The goal of the exploratory analysis is to provide cross-validated results from advanced modeling techniques used on a problem identified during the Analytics Assessment. The results then assist an organization to better understand how these methods can be applied to current business problems. Additionally, the Analytics Prototype provides a report that enables an organization to incorporate the results in their strategic planning for on-going analytic initiatives.
Elder Research works with an organization to define a representative sample of data suitable to demonstrate the performance of various predictive analytic algorithms. It is critical in prototype engagement to have a well-defined business problem to maximize the opportunity to provide valuable insights into the strategic use of analytics for the organization. In order to help minimize risk, Elder Research works with each organization to ensure a reliable target variable is identified that can be used to answer the business question.
We believe in focusing on the final objective from the outset of the Analytics Prototype project. To do this, Elder Research will work with key stakeholders to develop a set of evaluation metrics that will be used to assess the results of the predictive model built during this stage. These evaluation metrics will be jointly designed to show the overall usability and impact that predictive analytics can have when applied to the data. The final model and working code delivered will not be deployment grade. Additional development would be required to transition the prototype model into a deployable model.