Machine Learning in Energy
With an ever changing market place where does your pricing strategy align with technology? How often do you reprice your products? If it's less than per-deal you are likely losing margin. Pariveda has developed a Machine Learning approach to dynamic pricing that enables near continuous pricing. Read how we worked with a client to enable this capability.
Predicting Bid Wins leads to Better Deal Pricing
An oilfield equipment provider was concerned with wellhead price responsiveness during downturns in capital spending as a result of lower global oil pricing. They sought to build a predictive analytics solution which incorporated machine learning techniques to gain greater insight into the probabilities of winning opportunities.
Pariveda worked with the company to develop a cloud-based machine learning solution that used market conditions, customer information, and historical sales data to predict the win/loss probability across the pricing spectrum. The model was then converted into a web service and an Excel add-in was used to run data through it to produce a band of “valid” prices and their win probabilities. It used Jupyter Notebooks (powered by Python 3) extracted and transformed SAP data to feed the predictive Two-Class Boosted Decision Tree model.
Data-driven pricing decisions can now be made during the quote preparation process, enabling the bidding team to see what affect price changes have on win/loss probability for an individual deal. This new approach guides pricing, better informs sales and speeds up the quoting process. The Excel interface provides the marketing department with a mechanism to test various system configurations, market conditions, and customer segments.
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. We partner with Amazon Web Services to deliver solutions that provide value.
If you are looking for a partner to guide you along the Machine Learning journey, reach out to us at firstname.lastname@example.org .