Optimising Lead Generation with ML

Overview
Together with a leading financial institution, we developed and tested a new internal product, which leverages the power of classification and prediction machine learning models to automate the personalisation of sales lead generation in the bank.
The ChallengE
Our client relied on basic criteria like recent activity (last customer call) to identify new sales leads. However, this approach was labor-intensive, yielded low success rates, and overlooked specific customer needs. Moreover, it didn’t utilise the vast amounts of data the bank already had.
Seeking greater efficiency and effectiveness, the firm wanted to leverage existing sales data (including customer characteristics, transaction history, and industry requirements) to automate the generation of improved personalised leads.
Our Solution
The product we developed, deployed and integrated was based on a modelling approach that combines classification and prediction models. The interplay between the two enabled us to generate high-quality sales leads that are personalised and leverage the data the firm already had.
We also provided a comprehensive model card to improve the transparency and understanding. The card featured in-depth (versioned) documentation and user-friendly explanations based on feature contributions. This enabled us to ensure high interpretability of model predictions.
In addition, we rigorously tested the product with call centre end-users. The collected user feedback was incorporated into a closed-loop system to ensure continuous improvement of the model.
The Impact

Streamlined Workflow

by establishing clear roles and responsibilities for team members across three departments.

Empowered frontline staff

to become true advisors to their clients by identifying and prioritising leads of higher quality.

Codify set of sales routines

and best-practices across key journeys, embedded in a unified way of working

conclusion
Our product enabled the bank to better utilise existing client data so that the generation of more effective and personalised sales leads could be automated. Additionally, to ensure the model remains accurate and aligned with business and ethical objectives throughout its lifecycle, we established a closed feedback loop, ensuring its continuous optimisation.
FESTINA LENTE

Curious to learn more?

We would love to explore how we can partner with you on Data & AI initiatives for the benefit of your organisation, people and society

Reach out to us!
Designing futures for all of us.
Subscribe to our newsletter and we’ll keep you posted on our research, podcast and other AI goodies.
Thanks for subscribing!
Something went wrong with the submission.
AboutServicesWorkInitiativeInsightsAcademia
BlogResearchPodcastJoin usContact us
DEUS Amsterdam, Lauriergracht 112-C 1016 RR Amsterdam, NL
DEUS Porto, Rua Roberto Ivens, 288, 4450-247 Matosinhos, PT
DEUS A Coruña, Calle Ciudad de Lugo 35 - Bajo A 15004 A Coruña, ES
© 2024 DEUS.AI. All rights reserved.
Privacy PolicySustainability