A leading Personal Care Products Manufacturer employs Machine Learning to reduce late payments worth $3M per month

About

The client is a leading manufacturer and supplier of personal care products in the USA with operations across other regions like Latin America, Europe and APAC.

Challenges

The finance team of the client faced multiple challenges concerning its order to cash process. The order to cash process was inefficient due to unpredictable payment delays, time consumed in follow-ups by the collection teams and other indirect costs involved .The current invoice to cash process impacted the overall cash flows, EBITDA, financial health and hampered the overall strategic and financial planning initiatives.

Solution

Data Scientists from Tenzai followed a three-step approach to design a solution for the client.
The team first integrated the data from multiple sources like invoice, customer and product data required for analysis.

Then an in-depth exploratory analysis was conducted to extract key patterns and influencing factors about customer payment behaviour especially concerning delayed payments.

To identify the delayed accounts and timelines, a stacked ensemble model was built.

The first model employed classification algorithms to predict the propensity of payment delays for any given customer.

The second model built using regression techniques predicts the estimated timelines for the payment. The predicted results are displayed in an intuitive dashboard and made available to the collection team.

The collection team could identify accounts at risk, estimate delays and assess the overall impact on cash flow.

Based on the insights, the client can proactively reach out to accounts and plan their collection process.

Why not use data to gain insights, guide efficiency efforts, and make predictions? Contact us.

Results

Post-implementation, the client experienced a very high increase in terms of on-time collections across all regions.

The solution helped collection agents increase productivity, reduced collection expenses.

The solution helped the finance team to have better financial stability with predictable cash flows.
The other benefits include:

  • Improved collection timeliness by 10 days
  • Reduced the risk of late payment for invoices worth $3M / month
  • Reduced collection costs by 27%