Shopping Muse

Shopping Muse leverages AI technology to offer users an immersive in-store product discovery experience through interactive conversations and personalized product guidance. Powered by advanced deep learning, the system engages your users with natural language conversations. Whether they're searching for specific products, fashion styles, or gifts for special occasions or holidays, Shopping Muse provides tailored suggestions to meet their needs.

Onboard Shopping Muse

1.  In Shopping Muse, click Create Muse. 
2. A wizard appears to guide you as you customize various aspects of Shopping Muse behavior, appearance, and functionality:

• • • Tone of voice:  Select from four different assistant personas, each with its own style of communicating with customers. 
    • Muse icon: Appears as the assistant icon in various areas of the Shopping Muse interface.
    • Brand name: Provides context for Shopping Muse regarding the brand it is working for. 
    • Brand color: Defines the color scheme of the chat interface.
    • Muse name: Appears as the assistant name in various areas of the chat interface.

Upon successful completion of this process, the Shopping Muse dashboard panel appears.

Implement Shopping Muse

For a streamlined onboarding and implementation experience, Shopping Muse is designed to activate automatically every time a click is tracked on a designated HTML tag. There are two ways to implement these tags: Directly in the website codebase by your developers or using a Dynamic Yield personalization experience.  

Using a Dynamic Yield experience

With this method, you implement the Shopping Muse HTML tag through a Dynamic Yield experience. To simplify the process for you and reduce costly development time, we've designed pre-made templates that expedite the implementation effortlessly:

1. In the Web Personalization app, click New Campaign.
2. Select Multi-Touch.
3. Give the campaign a name.
4. Set the primary metric.
5. Create an entry point and define the insertion or trigger settings.
6. Use Muse predefined templates. Find them by filtering the templates by "Shopping Muse":
   Templates include:
   
   • Sticky Side Panel: Use as an evergreen entry point across all pages on both mobile and desktop (Dynamic Content).
   • Chat Bubble: Used as an evergreen entry point across all pages on both mobile and desktop (Notifications).
   • Small Banner: Used as a header, footer, or in-search modal skinny banner (Dynamic Content). 
   • Banner: Use as the main hero banner in a go-live promotion to educate customers about the new experience (Dynamic Content). 
7. Preview your entry point and ensure Shopping Muse is triggered upon click.
8. Repeat the process until all entry points are ready. 
9. Save the campaign as a draft until Shopping Muse is fully production-ready. 

Using manually embedded code

Using this method, you manually embed the HTML tag <dy-chat> to wrap your native entry point and open the Shopping Muse interface upon click. 

Customize 

Before going live, add customizations.

Click Customize to edit assistant behaviors you defined during the onboarding process and add additional advanced customizations to the look and feel. 

        

Available customizations include:

• Brand: Tone of voice, avatar (icon), and brand color.
• Text: Customize the welcome screen copy presented to users. Ensure the suggestion copies provide various examples of ways to communicate with Shopping Muse. 
• Products: Customize the appearance of a product tile and hide specific elements from product pages to create a slim quick-view modal upon product click.

How catalog images affect results

Shopping Muse suggestions are influenced by the type of images it's trained on:

• Wild Images: Product images featuring models in atmospheric or inspirational backgrounds, often including additional products. For example, a picture of jeans that also clearly shows sunglasses, a shirt, and shoes. In this case, the model focuses on recommending items that match the overall style and look represented in the image.
  If you use wild images, we suggest applying recommendation filters to align with the specific category of the item in context. </>
• Studio Images: Clear images of the product against a clean background. If a model is used, the product in question is the only fully visible item. The model prioritizes recommending similar products based on attributes like color, texture, material, and style. Studio images typically yield better results. 

Reporting 

The Shopping Muse report enables you to track and monitor the performance of important e-commerce KPIs (key performance indicators). These include sessions, revenue, purchases, add-to-cart events, and average order value (AOV). In addition, you can keep track of product clicks and conversions performed by users, helping you gain valuable insights into user behavior and campaign effectiveness. 

Limitations

• The model requires access to your image CDN to download and process your image. Have your technical team add the following IP addresses to your allowed list:
  • • 8.197.234.165
    • 3.127.189.219
    • 18.158.108.19

  • • 18.192.189.87
    • 18.195.163.252
    • 3.92.38.28

  • • 3.227.221.249
    • 54.145.37.112
    • 75.101.154.167
• If the CDN does not respond within 5 seconds for a specific image, that image is skipped. 
• Maximum image size is 10MB
• The image path must be explicit.
  For example:
  Correct: https://mydomain.com/myimage.jpg 
  Incorrect: //mydomain.com.myimage.jpg or //myimage.jpg 

FAQ

Can Shopping Muse work in any language?

The model we use for the Shopping Muse response is proficient in many languages. However, its performance tends to be best in the following languages:

Shopping Muse can handle many other languages with varying degrees of proficiency, including Arabic, Korean, Turkish, and more. The model’s capabilities are extensive but can vary depending on the complexity and nuance required in a specific language.

Product recommendation quality does not vary between languages. 

How does Dynamic Yield ensure that Shopping Muse is safe to use?

Shopping Muse incorporates multiple safeguards to ensure its responses are always brand-safe and aligned with your values. The model is trained specifically for each brand, guaranteeing consistency in voice and tone. Moreover, Shopping Muse only recommends products that are pre-approved by your team.

In addition, Shopping Muse employs a micro-service architecture. The product recommendation task, responsible for suggesting relevant products to the user, and the assistant task, which responds in natural language, are entirely separate. The LLM does not have access to product meta data. Therefore, Shopping Muse can't, for example, incorrectly claim that a specific product is available for free due to any penetration tactics.

Does Shopping Muse use PII to personalize the results?

All personalization calculations are done on Dynamic Yield servers and comply with regional limitations such as GDPR. Users' personal data is not shared with the LLM or third parties.

Can I review user queries?

Dynamic Yield has a zero retention policy. This means that no data is retained. 

Is my data used in any way to improve Shopping Muse?

No. No specific brand or user data is used for training Shopping Muse.