Deep learning

Deep learning is perhaps one of the most efficient AI tools for businesses looking to succeed in highly-digitized and fast-paced markets. Computers can use algorithmic models to analyze large amounts of unstructured and structured data better and faster than the average human, leading to greater...

To improve the gaming experience for players, a leading video game publisher sought to personalize in-game interactions, streamline model development, and increase long-term engagement and lifetime value (LTV) of users. Grid Dynamics addressed these challenges by implementing a reinforcement learni...

Customer retention is the primary pillar for building virtually any subscription-based business, including software, video game, media, and telecom businesses. Nowadays, it is common to use advanced machine learning techniques to predict customer churn probability as accurately as possible. However...

Faceted navigation, a.k.a. guided navigation is a de-facto standard user experience for any serious online retailer. Facets seamlessly introduce your customers to the structure and attributes of an online catalog and provide shoppers with powerful tools to slice and dice their results with useful f...

Online retailers are always looking for ways to provide delightful and frictionless shopping experience to their customers. Product discovery, powered by search and category browsing, stays at the top of the sales funnel and has the highest impact in converting visitors to customers.  At the...

Are only 20% of your product catalog recommendations behavior driven? Product recommendations have become an essential sales tool for e-commerce sites. These recommendation systems typically use collaborative filtering, a common approach for building behavior-based recommendation engines u...

“It takes months to find a customer, but only seconds to lose one.” Maintaining a high-quality customer service experience while minimizing costs is high on the list of any e-Commerce enterprise. An AI-based question-answering system can do just that. But how would one approach building such a...

Marketers usually use multiple channels–such as sponsored search, display ads, and emails–to reach their customers, and each channel usually includes multiple activities or has multiple parameters that are associated with various costs. For example, a marketer can run several email campaigns, each...

Modern customer analytics and personalization systems use a wide variety of methods that help to reveal and quantify customer preferences and intent, making marketing messages, ads, offers, and recommendations more relevant and engaging. However, most of these methods are designed to optimize only...

A customer of ours, one of the largest omni-channel retailers in the US, was having issues with product discovery. Their e-commerce site had a massive catalog with hundreds of thousands of SKUs, a modern e-commerce backend and a powerful search engine, yet the conversion was less than stellar. Fr...

The Solr suggester component allows you to vastly improve your search capabilities and experience. It provides users with automatic suggestions for query terms, and can be used to implement useful auto-suggest featurest in your search application.  … Searching grandchildren a...

Open source full-text search engines provide rich functionality out of the box. However, there are some use cases when naive implementation may lead to terrible customer experience. We faced one of such use cases when we worked with a patent management company.  Part of a patent officer's...

In our previous post, we discussed the impact of product misattribution in e-commerce and how image recognition with Machine Learning can be an important tool to resolve this issue. In this post, we will get into the details of how to detect and correct misattribution using Machine Learning, Goog...

A richly attributed and well-curated product catalog is the key asset of online retailers. However, products are frequently misattributed, which makes it a pain for customers to find the products they’re looking for. Catalog product attribution issues are a major pain point in e-commerce. They...

E-commerce customers often need to sort products by price, size, and other SKU-level attributes. Our job is to make this process as easy and pleasant for them as we can, because the more products they find, the more they buy. How do we help them find what they need?For general searching and facet...

In recent years, autocomplete has become a staple feature for searches of all types.Whether Google, Amazon, or smaller sites and vendors, predictive typing, as it’s otherwise known, (also sometimes called auto-suggest, search-as-you-type or type-ahead) has become an expected part of an engagin...

In previous posts we have discussed the steps needed to understand and prepare the data for Social Movie Reviews. Finally, it is time to run the models and learn how to extract meanings hidden in the data. This blog post deals with the modeling step in the Data Scientist’s Kitchen. At the...

There is a broad and fast-growing interest in data science and machine learning. It is fueled by an explosion in business applications that rely on automated detection of patterns and behaviors hidden in the data, that can be found by software and exploited to dramatically improve the way we mark...

As we explained in our introduction to this series of posts, we are exploring a data scientist’s methods of extracting hidden patterns and meanings from big data in order to make better applications, services, and business decisions. We will perform a simple sentiment analysis of a real publ...

I was recently on an airline flight with onboard entertainment. There was a good selection of movies, but look at the film navigation menu! It lacks the ability to nest different languages into a single movie item and facet selections based on the movie’s language. As a result, it wastes scre...

We’ve talked about searching nested parents and children with Solr Block Join. But we can go far beyond that, to searching siblings, grandchildren, and other descendants. This gives your customers more search options without forcing them to do a new search every time they add a search parameter....

The “law of unintended consequences” applies to using the block join query parser in Solr, just as it does to many other things in life (and software). Leave out certain query strings in Solr, and It seems to make no difference. … Searching grandchildren and siblings with Solr block join...

SolrInputDocument has methods — getChildDocuments()and addChildDocument() — for nesting child documents into a parent document. XML and Javabin formats are now able to transfer them. JSON support is ongoing. Start by indexing a few t-shirts, as a sample product-SKU hierarchy us...

In a previous post, we talked about business motivations behind the support of structured documents in a Solr/Lucene index and the unique requirements for a  faceting engine which is created by this approach to modeling data. We have introduced SOLR-5743. Now it is time to take a deep di...

Join support is a highly-requested Solr feature, especially in e-commerce. So I repeated Erick Erickson’s benchmark test with block join support for Solr, and I want to share my observations on how BlockJoinQuery can maximize Solr/Lucene performance.  In this post and in the future,...

A straightforward look at how block join faceting works, how it can save your customers from frustrating search experiences, and why Grid Dynamics created SOLR-5743 to bring block join faceting to Solr Here is a simple type of faceted search you see on many e-commerce websites: In this ex...

Solr/Lucene has emerged over the last few years as a leading open source search platform for large-scale e-commerce search engines. Systems based on Solr power major sites including Macy’s, Kohl’s, Walmart, Etsy, and many others. An increasing number of tier-1 digital retailers are building their...