How We Do It

Marketing and
Data Science

Our industry-leading Marketing and Data Science (MaDS) team applies state-of-the-art modeling and analytic techniques against a multitude of data streams to solve your toughest business challenges. More than just number-crunchers, our MaDS team brings tech-enabled methods and a smart voice to problem-solving.

Problems We Solve

With your objectives as the north star, our experts know the advantages and limitations of different methodologies and analytical techniques, when to adapt approaches and how to create new solutions in service of your business questions.

Market Segmentation and Clustering

When you need to group people, needs, or occasions for effective targeting we’ll apply the most appropriate clustering techniques whether it be k-means, hierarchical, two-step, prototype, or archetypal, and then apply opportunity analysis to guide your priorities.

Path to Purchase Sequencing

Our proprietary sequencing methodology, derived from a technique used in genetics, allows us to classify people into different journey groups and identify key leverage points, allowing you to target and activate each journey.

Learn More

Big Data

Given the volume, variety and velocity of big data we’re focused on accessing the relevant data and harmonizing multiple data streams such as attitudinal survey, monitored digital behavior, and longitudinal financial performance to derive insights.

Learn More

Prediction and Simulation

Every marketer is trying to identify which levers to pull to create a desired outcome. Whether it’s regression, survival analysis, Bayesian networks, structural equation models, agent based models, optimization, or TURF, we’ve got you covered.

Dimension Reduction

More is not always better. When building models, we need to eliminate the noise and need to synthesize the movement between a high number of variables. We can use PCA, factor analyses (exploratory and confirmatory), community detection, correspondence analysis, multidimensional scaling and other approaches to get the best use of big data.

Trade-Off Models and Experimental Designs

Optimize products, menus, shelves, and more by using analytic methods that put consumers in context and simulate purchase decisions. Use conjoint analysis, discrete choice models, allocation models, or maxdiff to estimate preference and unique contributions to choice.

Market Segmentation and Clustering

When you need to group people, needs, or occasions for effective targeting we’ll apply the most appropriate clustering techniques whether it be k-means, hierarchical, two-step, prototype, or archetypal, and then apply opportunity analysis to guide your priorities.

Path to Purchase Sequencing

Path to Purchase Sequencing
Our proprietary sequencing methodology, derived from a technique used in genetics, allows us to classify people into different journey groups and identify key leverage points, allowing you to target and activate each journey.
Learn More

Big Data

Given the volume, variety and velocity of big data we’re focused on accessing the relevant data and harmonizing multiple data streams such as attitudinal survey, monitored digital behavior, and longitudinal financial performance to derive insights.
Learn more about UCLA Social Sciences LRW Big Data Partnership
Learn More

Prediction and Simulation

Every marketer is trying to identify which levers to pull to create a desired outcome. Whether it’s regression, survival analysis, Bayesian networks, structural equation models, agent based models, optimization, or TURF, we’ve got you covered.

Dimension Reduction

More is not always better. When building models, we need to eliminate the noise and need to synthesize the movement between a high number of variables. We can use PCA, factor analyses (exploratory and confirmatory), community detection, correspondence analysis, multidimensional scaling and other approaches to get the best use of big data.

Trade-Off Models and Experimental Designs

Optimize products, menus, shelves, and more by using analytic methods that put consumers in context and simulate purchase decisions. Use conjoint analysis, discrete choice models, allocation models, or maxdiff to estimate preference and unique contributions to choice.

Client Results

Our Clients

Let’s Connect

  • This field is for validation purposes and should be left unchanged.
Hi! We're glad you're here. LRW is now part of Material,
and our site will be migrating to materialplus.io in the near future.
Bookmark me!