Demand forecasting, route optimization improves order pick-up efficiency by 50%, new customer acquisitions by 20% for a tyre management company

Demand forecasting, route optimization improves order pick-up efficiency by 50%, new customer acquisitions by 20% for a tyre management company Banner

Client Profile.

A global waste tyre management company involved in the collection and disposal of scrap tyres.

Business Needs.

The company was struggling to accommodate a growing demand for scrap tyre collection services in the region, crucial for their expansion plans, while continuing to maintain its reputation in delivering industry-leading pick-up frequency.

The client was using a manual forecasting solution, which had an error rate of +/-50%. And was looking for a solution that could help them forecast tyre volume within +/-10% at individual client level. And connect it with a route optimization tool to be able to serve more clients without an increase in fuel costs.


Limited access to historical data: Historical tyre order data available of less than a year as well as large variations in available data

Data silos and quality issues: Gaps in information availability on several parameters such as the truck availability and growth in the service area, competition, customer attrition, etc.

Data preparation issues: Available data was spread across multiple systems using different process / standards for data capture, making consolidation of all the data a tricky task.


Designed Order forecasting and Route optimization solutions, which included

  • A user interface to enter daily tyre volume for each client along with any other changes in underlying data.
  • A dashboard showcasing useful KPIs such as tyre volume and its growth across clients, geographies, client segment, time-period etc. along with actionable insights such as any patterns / trends / out of pattern etc. and alerts based on pre-specified criteria.
  • AI-based route optimization application which connected to order management solution and extracted data on clients to be served on any given date along with the expected number of tyres to be collected. The application identified the firm’s physical locations using geospatial data and recommended the best route.
Campaign Management Challenges


The following steps were taken to address data quality, quantity and consolidation issues:

  • New source identification for information such as the number of vehicle and its growth used in the service area, competition, sales and marketing initiatives.
  • Developed custom tool to automate the process of integrating data sources.
  • Employed extensive data cleansing to ensure accuracy for machine learning algorithms.

Selected machine learning / deep learning methodologies using Neural Networks. The solution enables estimating order frequency and volume at individual client level. This involved simulating very large number of iterations (somewhere around 10,000+ models) across different set of advance ML methodologies (Neural Networks) and different parameters to achieve satisfactory level of accuracy (+/- 10% average error).

Business Impact.

50% Increase in order pick-up efficiency
20% New customer acquisitions
80% Decrease in number of client complaints
24% Increase in revenue
Share your Challenges Email us!

Call us now!


Connect with us

Facebook Icon linkedin icon twitter icon