We help leading retailers and brands to create personalized shopping experience across online, mobile, and in-store using data-driven methods and machine learning.

Use cases


Optimize acquisition campaigns

We build models for media mix optimization and multi-touch attribution that help to optimally allocate budgets across the channels and set specific channel parameters such as keyword bids. This helps to improve the effectiveness of acquisition campaigns and individual channels.


Improve conversion rates for new visitors

We build customer intelligence platforms that personalize the experience of unregistered visitors based on their in-session behavior and device and location data. The models used in these solutions also identify customers with a high propensity for cart abandonment and prescribe the best mitigating action.


Take upsell and cross sell to the next level

Our personalization platforms provide a wide range of models including personalized and non-personalized product recommendations, propensity to brands and styles, price sensitivity scoring, sentiment analysis, and more. The signals produced by these models can be used to personalize every aspect of  customer experience and improve the effectiveness of offers, promotions, and notifications.


Implement innovative personalization features

We help our clients to implement innovative and industry-specific personalization use cases that account for local events and trends, customize samplers and multipack products, and even reduce shipping costs by accounting for available space in a box.


Improve customer engagement strategically

We use state-of-the-art machine learning methods to optimize each marketing action in a long-term context and make all actions contribute to the long-term improvement of customer experience, loyalty, and value.


Analyze customer journeys

One of the main benefits of customer intelligence is the ability to quantitatively analyze customer journeys, understand what drives certain customer behaviour, and determine how the level of engagement can be improved. Our customer intelligence software provides multiple tools that quantify customer lifetime value, suggest personalized next best actions, and estimate the contribution of various touchpoints.

Our clients

Finance & Insurance

Customer data management

data platform

Customer 360

Our personalization and analytics solutions include comprehensive customer data management capabilities to consolidate, clean, validate, and enrich customer data at any scale, providing a 360° view of a customer.

ml platform

Rapid AI/ML productization

We build data science and machine learning platforms that automate experiment tracking, model versioning, feature management, and production model deployment. Our platforms also include capabilities designed specifically for customer-related use cases that speed up the development of analytics and personalization applications.

decision engine

Real-time audiences

We build pipelines that collect, process, and aggregate customer events in near real-time, continuously providing up-to-date customer profiles to the decision-making components. The scoring models and segmentation rules are also evaluated in real time to optimize customer experience based on micro-moments.

How to get started

We provide flexible engagement options to help you build a successful customer intelligence solution faster. Contact us today to start with a workshop, discovery, or proof of concept.

How our customer intelligence platform works

Powerful array of models
Under the hood, we provide a comprehensive array of models that determine best product recommendations, preferred brands, styles, and channels, expected lifetime value, and optimal offers. These models can serve multiple B2C and even B2B use cases.
Central decision engine
Modern personalization technologies allow us to optimize hundreds of customer experience elements such as recommendations, product catalog and navigation, special offers, push notifications, and many others. Our personalization platforms are designed to operate as central decision engines which support this wide range of use cases in omni-channel environments.

Learn more

How deep learning improves recommendations for 80% of your catalog
In this article, we discuss how traditional targeting and personalization models such as look-alike and collaborative filtering can be combined with reinforcement learning to optimize multi-step marketing action policies (aka Next Best Action policies). These techniques can be applied to various business problems such as customer retention, customer experience optimization, and promotion targeting.
Read more
Customer2Vec: Representation learning for customer analytics and personalization
In this article, we focus on the learning of useful semantic representations (embeddings) for products and customers using neural networks. These embedding vectors then can be used as features in the downstream propensity and recommendation models, help to perform better customer analytics and segmentation, and speed up the development of customer intelligence software.
Read more
Building a Next Best Action model using reinforcement learning
This tutorial describes how to optimize sequences of marketing actions strategically. We use reinforcement learning concepts to build a prescriptive model that identifies next best actions among several alternatives.
Read more
Read more on data science for retail and brands

Would you like to learn more about economic and algorithmic foundations of customer experience optimization? We published a 500-page book on enterprise data science that is available for free download, and there are several chapters on personalization in it.

Read more on advanced customer intelligence

This report provides an overview of recent advances in customer intelligence by examining 10 industrial case studies. These case studies were selected from the consulting practice of Grid Dynamics and public reports to cover the most important, common, and innovative trends in data science and machine learning methods used in modern customer intelligence and marketing analytics. The report covers the following four major areas of active research and industrial adoption:

  • Deep learning models that incorporate a wider range of signals and data, including textual and visual data.
  • Deep learning models that process sequences of events, including User2Vec models.
  • Reinforcement learning models for the dynamic and strategic optimization of marketing actions.
  • Econometric and deep learning models that quantify financial and operational risks.

We have made this analysis publicly available to help practitioners build successful customer intelligence solutions using the latest technologies.

Get in touch

If you have any additional questions, please feel free to reach out to our experts directly

More enterprise AI solutions

Get in touch

We'd love to hear from you. Please provide us with your preferred contact method so we can be sure to reach you.

Please follow up to email alerts if you would like to receive information related to press releases, investors relations, and regulatory filings.

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.