Sign up for our newsletter and get the latest big data news and analysis.

Predicting the Crunchiness of a Chip

Cruchiness_of_a_Potato_chipEffectively utilizing valuable corporate data assets is the key to success with data science projects. One Canadian consulting company that specializes in multivariate analysis, ProSensus, offers a rather unique case study that demonstrates how to predict the crunchiness of a chip. Textural properties of snack foods are essential to customer satisfaction but they are very difficult to measure. Multivariate modeling of acoustical sensor data can be used to effectively predict these important properties in real-time at low cost and without interfering with the process.

Snack food producers knows the importance of textural measurements such as blister level and crunchiness on “mouthfeel” and customer satisfaction. Traditionally these are measured using sensory panels, meaning that only a tiny subset of the chips are analyzed and at large expense. The goal of the highlighted case study was to determine the optimal way to characterize chip texture and predict this using multivariate analysis of acoustical sensor data.

This research project was successful. First, the chip’s quality was quantified by combining the results of a sensory panel, visual appraisal and mechanical breaking force through a multivariate analysis. The two calculated properties (chip brittleness and blister level) were then accurately predicted from an acoustical sensor installed on the process. Work is currently underway to commercialize this promising technology.

To read more about the specific approach used by ProSensus, click HERE.

 

 

 

Leave a Comment

*

Resource Links: