Related Items

Item-to-item recommendations are a crucial element in improving the user experience and a feature that can be deployed very quickly. Each time a user browses a PDP on your website, similar items aligned with the user’s taste are recommended, creating an excellent opportunity to keep them engaged. The goal is to serve users the most targeted, relevant “similar items” on each page to increase the engagement, time on site, and retention.

Dashboard

By entering a specific Item ID, you can view and evaluate the “similar” items returned by the API and filter those recommendations.

‍

‍

Selecting a Product ID

‍

On the top side of the screen, you will find an input field where you can enter a product ID, if you now a specific product id. You could aslo click on the "Pick Item ID" button to randomly select an item and evaluate the recommendation provided.

Once the ID is entered, the system will fetch and display similar item recommendations on the main panel. Each recommended item will come with related details and properties for a comprehensive understanding.

‍

Evaluating Recommendations

The central panel is the heart of the evaluation process where the recommended similar items are displayed. Once a product ID is entered, the system will generate a set of recommended items. By default, ten recommendations are displayed, providing a balanced perspective on similar items.

‍

To ensure a tailored user experience, you can easily adjust the number of displayed recommendations to suit your evaluation needs. Simply select a desired count from the dropdown menu located at the top of the panel. Whether you prefer a deep dive into a wide range of similar products or a focused evaluation of a few key items, you have the flexibility to customize the count as per your requirements.

‍

Moreover, we offer two distinct display modes to enhance your evaluation experience - List View and Grid View.

List View: This is an information-rich mode where each recommendation is presented alongside its full list of properties. From product description, price, brand, to category and more, all crucial product details are displayed. This exhaustive information can offer valuable insights into why a particular item has been recommended, enhancing your understanding of the recommendation logic.
Grid View: This mode offers a more compact and visually appealing layout, mirroring the user experience on an e-commerce site. While it provides less detail about each product compared to the List View, the Grid View allows for quick and easy navigation through the recommendations. It's particularly useful when you want to assess how the recommendations would appear to a user in a carousel or grid setting on your website, aiding you in visualizing the customer experience.

Thus, with adjustable recommendation counts and adaptable viewing options, the 'Evaluating Recommendations' process in Beam Studio allows you to assess the effectiveness of your similar item recommendations in a flexible and user-friendly environment.

Recommendation Types

The Beam Studio dashboard is meticulously designed to help you navigate through various features smoothly. A key part of this is the right-side panel, which provides several configurable options to help you tailor your recommendations. Let's go through these features in detail:

On the right-side panel, you will notice three headers, each representing a distinct type of recommendation model that you can evaluate. The availability of these models is based on the custom setup our team has established for you:

Regular: The default recommendation model, shaped by user behavior and preferences, coupled with the business rules you've implemented. This flexible model allows for extensive adjustments to tailor your recommendations.
Pre-computed: Optimized for performance, this model provides pre-calculated recommendations. Due to its nature, the only adjustable parameter is the scenario; all other business rules are fixed to maintain the pre-computed model's accuracy.
Context: An advanced recommendation type allowing greater customization. Alongside the standard business rules, you can define 'items' that you want the recommendations to resemble or aim towards, adding an extra layer of personalization.

Regular Filters & Scenarios

To optimize the performance of our recommender system, it's crucial to understand and fine-tun business rules to your specific needs. While our dedicated machine learning engineers at Crossing Minds initially set up these rules, we believe in empowering you with the knowledge to adapt these guidelines for your unique business objectives.

The Beam Studio dashboard offers several ways to adjust these business rules:

Scenarios: A scenario is a comprehensive set of business rules that provide a strategic framework for your recommendations. Scenarios encapsulate filters, exclusion rules, algorithms, and candidates preselection to produce a tailored recommendation system. You can select the most appropriate scenario for your business model from a predefined set, or even create custom scenarios to cater to specific business requirements. Swapping scenarios allows you to swiftly shift the complete approach of your recommendations before delving into the finer details.
Algorithms: These are the parameters that are fine-tuned to select the most suitable recommendation model. They are usually set by our machine learning engineers.
Filters: Use filters to refine the recommendations by including only items that fulfill certain conditions based on their properties.
Diversity : This unique feature allows you to apply a diversity score to each property of a product. This score influences the variety within the recommendations, allowing you to enhance the breadth of suggestions based on specific attributes, thereby promoting a more diverse product offering.

Remember, the key to effective recommendations lies not just in the algorithms but also in the configuration of these business rules. By understanding and adjusting these parameters, you can fine-tune the Beam recommender system to best suit your business needs.