Of the roughly 22,000 materials in our database, 80% have fewer than half of the traditionally reported processing parameters. When our users are trying to determine how to set their machines, the lack of reported information forces them to compare against similar materials, or guess. Not only does playing this "guessing game" cost valuable time, it also increases risk, so we decided to help our users by implementing machine learning.
To provide the injection molders with additional resources and information, the Mobile Specs team developed this new ground-breaking technology to leverage information available in the database from material suppliers. By creating advanced machine learning algorithms to generate predictions about missing data, we have been able to identify trends in the data to fill in several missing values.
Please note that the values generated from machine learning are predictions. These additional data points are not provided by material suppliers. However, the predicted data should provide processors with confidence since the average error for predicted data values is approximately 5%. (More conservatively, we expect that for 95% of the materials, the true value will be within 15% of our predicted value.)
The predicted values from our machine learning algorithms are not provided by the material suppliers. They are estimates that Mobile Specs has generated in-house with our proprietary Machine Learning technology using publicly available information from the material data sheets.
Do you have questions about our data predictions or machine learning algorithms? Feel free to contact us.