One-to-one engagement powered by machine learning
With mParticle, Overstock is able to deploy machine learning models rapidly on a solid data foundation.
Since 1997, Overstock has provided customers with an easy way to purchase both everyday and hard-to-find furniture and home decor items at the best prices. A decade after its founding, faced with increased competition and rising customer acquisition costs, the company embarked on a company-wide initiative to optimize its return on marketing spend.
To harvest insights from Overstock’s massive customer dataset, the team went in search of an agile, scalable data modeling solution, but quickly encountered a more foundational challenge: their customer data sets were stored in numerous disparate systems, with no universal linkage across them. Without clean consistent data readily available, even the best machine learning would be of little use.
After an exhaustive review, Overstock selected mParticle as the customer data platform to collect, cleanse, and normalize their data before feeding it to their machine learning engine.
After training the models and scoring individual records, Overstock’s machine learning engine then writes the modeled values as user-level attributes, back into mParticle, where they can be leveraged to drive marketing actions.
mParticle has enabled Overstock to model customer data and score individual customers across hundreds of dimensions. The machine learned attributes include: channel propensity, category and product affinity, expected conversion propensity, expected purchase value, and expected lifetime value, among many others.
With mParticle, Overstock was also able to decrease machine learning model deployment cycles from three months to one day, enabling them to continue pushing the boundaries of machine learning powered AI, while creating highly differentiated customer experiences.
Using the scored values, non-technical marketers have created and deployed custom segments that have led to a 10% increase in overall marketing efficiency.
Latest from mParticle
mParticle Linting: Real-time event feedback for a cleaner data pipeline
mParticle Linting enables you to statistically analyze code against your data plan as you develop, making it easier to adhere to your company’s data plan and ensure that high-quality data is logged to your mParticle data workspace.
Between two firms: Featuring Hull and mParticle, moderated by the CDP Institute
If you've ever wondered about CDPs and the role they play in both B2B and B2C industries, now is your chance to hear it straight from the source! Join Michael Katz (CEO and Co-founder of mParticle), Romain Dardour (CEO and Co-founder of Hull), and David Raab (Founder of the CDP Institute) on 8 July at 11:30am PT/ 2:30pm ET/ 7:30pm BST for a chat between two of the leading CDP firms.
Tech for Black Founders
Today, only 1% of founders backed by venture capital in the United States are Black. This is appalling and shows how the odds are stacked against Black technologists and entrepreneurs. The onus is on us in the tech community to start evening the odds. In an effort to provide concrete, long-lasting support, Amplitude, Branch, Braze, Radar, and mParticle are coming together to make our software completely free to U.S.-based, early-stage startups led by Black founders.
The Customer Data Platform Comparison Tool
Selecting the right Customer Data Platform for your team is an important decision, but your evaluation doesn’t have to be a complex process. Use this comparison tool to prioritize the platform features that are most important to you and track how different vendors compare.