Back to Talks

Modeling Behavioral Patterns of Consumers Seeking Legal Services

Michael Terry Lawfty

Audience level: Intermediate
Topic area: Case Study

Description

We present a case study on how our data team models and optimizes the behavioral patterns of consumers seeking legal services. By linking together the regional offline & online consumer data into a common model, we are able to optimize digital advertising investment, and take advantage of time-of-day and location-based opportunities, in arguably the most competitive Google Adwords vertical.

Abstract:

Introduction - The Problem

US consumers are bringing more information about their lives online via their smartphones and cloud-based apps. These individuals and groups are increasingly expecting on-demand solutions to their needs, including those in sensitive legal areas. In this opener, we will present our thesis that there is an increased demand from consumers to seek out vendors that provide quick and easy transactions online.

Despite significant financial incentives to do so, legal service providers are not keeping up with the pace and expectations of consumers and their use of technology and rapid, informal communication. Without tech-enablement of their online marketing and consumer relations management, consumer-facing law firms are not able to effectively service their clients and survive the increased competition.

Significant technology investment is (currently) encumbered in regulations, thus preventing disruption of the status quo in the legal industry.

Lawfty - A Case Study In Modeling Consumer Behavior

The Training Data and Modeling

Our system is based on 4 years of consumer web search data linked to the conversions into legal intakes.

Code/Demo: We use filtering and hour-of-day K-Means clustering on our training data to prepare samples for training.

With enough samples, the model can predict relevant inquiry rate.

Optimizing Ad Spend with Models

We optimize our advertising spend across these clusters to maximize the expected return.

Conclusions

Summary of Clustering and Cost Optimization

The Future of Behavioral Targeting for Consumers Seeking Legal Help