Predictum Blog

Nov 14, 2017

The Recipe for Success in Research and Experimentation

This is the third of three posts in a blog series, which is associated to Predictum’s on-demand webinar, Reactivating Your Dormant Data to Extend its Business Value.

In this post, Wayne J. Levin shares his recipe for success in research and experimentation with the use of SashLAB™, our solution for advancing innovation, productivity, and knowledge in R&D.

R&D teams in companies are constantly looking for ways to better leverage research methods to improve their knowledge-worker productivity. Whether companies use the design of experiments (DOE) method or conduct experiments more informally in new product development, they can advance their new product development much further with the use of digital experimentation and a virtual lab solution.

SashLAB, our next-generation virtual lab, employs robust features and responsive performance to help you mobilize your researchers with enhanced flexibility, effectiveness, and creativity. It helps experimenters focus on the subject matter at hand, designing and evaluating better experiments, without the impediments of analytical jargon that come with using advanced statistical methods.

In our upcoming webinar, we’ll give a demonstration of SashLAB in action with the design of experiments (DOE) method and historical data to show how to build models and optimize experimental outcomes. We’ll provide a use case with example data for compounding and formulation, but our solution is customizable to meet the particular requirements of individual companies.

Some of SashLAB’s key features that we’ll highlight in the webinar are essential ingredients for boosting day-to-day productivity and gaining insights more quickly in experimentation.

Search by past experiments for similarity by recipes or performance properties – You can extend your reach in searching for similar recipes from historical data to be compared to a given recipe in an experiment. The search feature enables you to rapidly search high volumes of historical data and filter the search results by a customizable range of similarity. For example, if you search past experiments for 75% to 100% in recipe similarity, you can compare ingredients and select which ones are suitable for designing new experiments. In another example, you can search by performance properties (objectives) to find out which recipes from past experiments achieved those objectives or came close.

Search for recipes and ingredients in designing a new formulation

Search for recipes and ingredients in designing a new formulation

Change a multitude of input factors and conditions at time – You can change a multitude of input factors and conditions at a time to determine the best possible outcomes for an experiment. In a physical experiment, an experimenter may be limited by the ability to change only a small number of input factors and having to wait several weeks for the results. With the use of SashLAB, you can change a larger number of input factors at a time and view how they affect the output results almost instantaneously.

Visualize and adjust the interactions between the parameters of an experiment – SashLAB’s data visualization features enable you to view custom-built models graphically according to your defined parameters for recipes, performance properties, and input factors. You can view interactions between parameters with click-and-drag capabilities for adjusting the levels of interaction.

Visualization of the interactions between parameters of a designed experiment

Visualization of the interactions between parameters of a designed experiment

Capture successive configurations of an experiment on the fly – The Snapshot feature enables you to capture each configuration of an experimental design on the fly as you adjust various parameters. Once you have generated a baseline of snapshots, you can select the most promising designed experiments to be promoted to a physical lab for testing.

Among the benefits of using SashLAB in experimentation are time savings, cost reduction, and higher quality. You can compare and contrast the parameters of an experiment and its resulting outcomes in a matter of hours or days, compared to weeks in a physical lab.  You can rapidly run several digital experiments in succession without incurring needless costs associated to physical experimentation.

Also, SashLAB helps you to ensure that experiments are fully vetted before they go live in the physical lab. With ever-increasing competition in getting products to market faster, SashLAB can help you foster innovation and experience shorter experimental cycles in new product development.

Is SashLAB a viable solution for your company to accelerate research and experimentation to achieve substantial gains in knowledge-worker productivity? To receive more information on how SashLAB can be customized to meet the requirements of your company or industry, get in touch with us.

Wayne J. Levin is President and CEO of Predictum Inc. Connect with Wayne on Twitter and LinkedIn. Also, connect with Predictum Inc. on Twitter and LinkedIn.

For more of this blog series, catch our first post Dormant Data Equals Lost Opportunities, and our second post, Behind the Scenes of High-Volume Data Extraction.


Share this: