Price Variance Analytics

IndustryEnergy and Utilities

Year2017

RoleMachine Learning, Enterprise Bot

TechnologyPython, Pandas and Numpy, Plotly, In-house pattern recognition algorithm

Identify patterns in noisy purchase data.
To provide timely insights.

A US-based MNC client of ours in the energy and utilities space wanted to spot patterns in their noisy purchase data to calculate purchase price variance. The aim was to provide price intelligence on suppliers.

Solution

The power to predict.
Gives you wings to fly.

Solution

We came up with a Machine Learning algorithm to identify parts in the noisy data identical to the observed patterns. We also created a tool (with easy drill-down and explorative navigation) to help visualize the purchasing data and a prediction engine to predict the right price for a part.

IMPACT

AI powered smart bots.
Improves productivity and quality of decisions.

The company was, thus, able to see a 10% improvement in identifying cost-saving opportunities. Insights served as pointers to decisions, expected result, and standard deviation.

We use cookies to provide you with a better experience. By using our website you agree to the use of cookies as described in our Privacy Policy.