Pariveda and Databricks
Pariveda is proud to partner with Databricks. As a leader in the Machine Learning space, Pariveda leverages the Databricks platform with clients to optimize their experience and workflow with Machine Learning. Databricks enables businesses to access data at scale, deploy production-quality Spark applications, and leverage data science in decision-making.
Let's work together to optimize your data, scale it for current and future use and make decisions that benefit your customers. Email us at firstname.lastname@example.org and mention Databricks so we can put them to use on your next implementation.
Learn how we used Databricks and Machine Learning in Manufacturing
What are the processes in place right now that are causing you to rethink strategy? As a large manufacturer you are constantly dealing with the assembly timeline, the different suppliers and satisfying customers when there is a fault in the product. How do you collect from suppliers when their parts cause a warranty claim? If you have a process how well are you leveraging that capability? Pariveda has developed a Machine Learning approach to predict claims that are supplier-at-fault, which could help you recover millions. Read below how we helped a client find a potential recovery amount over $7M.
Managing Warranty Claims With Benefit Back to You
When this heavy equipment manufacturer gets a warranty claim, often a part supplier is at fault, and some contracts allow them to recover money from the supplier. Today, this manufacturer recovers money on only 3% of claims. It is estimated that 12-13% of claims could be recoverable, amounting to a reduction in warranty liability in the $10M range.
Pariveda worked with this manufacturing company to develop a cloud-based solution using a Machine Learning model to predict which claims will be accepted by suppliers, and to mark these claims for submission. The model was trained using the set of claims that had been submitted to suppliers based on the existing process using a fully automated platform to enable retraining, ensuring that the model keeps up with current trends. Model execution is also fully automated, running daily over the claims that have been submitted. The Databricks Apache Spark™ platform was used for data engineering, with model training and execution built on Amazon SageMaker using the platform’s built in XGBoost algorithm.
In initial back-testing of warranty claims submitted during 2018, the model predicted that over $13M of claims that were not submitted to suppliers would have been accepted, with a potential recovery amount of over $7M.
Pariveda's ML Methodology
Our overarching principle in our AI/ML engagements is to help our clients build a sustainable AI/ML capability through a holistic view of the people, process, and technology required to support that capability.