Optimization of Google Shopping Feeds with OpenAI’s ChatGPT: A Comprehensive Guide

In the highly competitive e-commerce market, high-quality product data is crucial for success. Accurately displaying product details not only improves search engine visibility but also the customer experience. However, creating and maintaining this data can be challenging, especially in industries with rapid product changes and small batch sizes. This is where artificial intelligence comes into play, enabling processes to be optimized and made more efficient. The GPT Feed Creator is a tool based on a Google Sheet with Apps Script that enables communication with OpenAI’s ChatGPT. It automates the optimization and enrichment of product data. This powerful instrument uses ChatGPT not only to improve the quality of product data but also to accelerate its creation and updating, making it ideal for dynamic market segments.

Video for the article

You prefer the audio? Watch the video.

The Challenge: Good Product Data is Hard to Create

Many online retailers face the problem that creating and updating product data is time-consuming and error-prone. Especially in niche markets or with rapidly changing assortments, it can be almost impossible for retailers to continuously generate high-quality data. However, insufficient or outdated product information often leads to poorer search results and a lower conversion rate.

Generative AI to the Rescue

The solution to this problem could lie in generative artificial intelligence (AI). OpenAI’s ChatGPT can be used to enrich existing product data with generated content or extract attributes from the description. By implementing an AI-supported feed creator, texts can be generated and optimized automatically, improving data quality and significantly reducing data maintenance effort.

The creation of the GPT Feed Creator: From theory to practice

The use of ChatGPT to optimize Google Shopping feeds is an exciting example of how theory and practice can converge in the world of artificial intelligence. Therefore, we provide a deeper insight into the development of the tool here.

Feasibility Test in Python

First, a feasibility test was conducted in Python to understand how well the existing product data is suited for automated processing. The reason for this decision was the existing OpenAI Python Library, which initially saves a lot of development work. This test helped to recognize the limits of the current data quality and identify the need for more precise data preparation.

Prompt Engineering

After the feasibility test, we moved on to prompt engineering. We developed specific prompts that OpenAI’s ChatGPT could use to generate the desired product descriptions. This step required a deep understanding of the product features most relevant to customers, as well as SEO principles that maximize search engine visibility. One particular hurdle was that the AI response had to be in the correct JSON format. This issue has now been resolved by OpenAI, as it now has the response_format parameter that clarifies this.

Workflow Optimization

With the insights from the initial tests, further optimizations were made to the workflow. The goal was to increase efficiency, improve the reliability of the generated data, and bring the entire process to production readiness. This included technical adjustments to the code, the integration of additional data sources, and continuous monitoring of our system’s performance.

Implementation and Tests

The final phase before full implementation included extensive testing with various product categories and customer feedback, as well as performance monitoring. These tests were crucial to ensuring that the GPT Feed Creator works effectively not only in theory but also in real-world applications. They helped eliminate teething issues and make the application more user-friendly.

The creation of the GPT Feed Creator is a prime example of how innovative AI technologies can be applied to solve real problems in e-commerce. Through this process from theory to practice, we have created a solution that not only simplifies product data maintenance but also sustainably strengthens our customers’ market position.

Practical example: Optimization of product data in the online shop for women’s fashion

The application of artificial intelligence to improve product data can be illustrated particularly impressively with a concrete example from an online women’s fashion store. In this case study, we focus on the optimization of the data for a shirt from the brand “VIA APPIA DUE.”

Initial Situation

The original product data was relatively simple and not entirely geared toward search engine optimization. The product title was “VIA APPIA DUE Shirt – Red Multicolor – Size 46.” While this information was basic, it lacked important details that could improve both search engine optimization and the customer experience.

Optimization Process

Using the GPT feed creator, the product data has been extensively revised. The product name has been updated to “VIA APPIA DUE Women’s Round Neck 3/4 Sleeve Shirt Red Multicolor Size 46,” which is not only more precise but also more appealing to potential buyers. Additionally, the product description has been expanded to highlight the shirt’s special features and benefits, such as its comfortable fit and striking design.

Result

The revised data not only emphasizes important selling points but is also designed to be more SEO-friendly. This leads to better visibility in search engine results and potentially a higher conversion rate. The following table shows a direct comparison of the original and optimized product data:

Attribute	Original data	GPT-optimized
title	VIA APPIA DUE shirt – red multicolor – size 46	VIA APPIA DUE Women’s Round Neck 3/4 Sleeve Shirt Red Multicolor Size 46
Description	No detailed description available	Experience stylish comfort with the VIA APPIA DUE Women’s Round Neck 3/4 Sleeve Shirt in Red Multicolor, Size 46. This versatile shirt adapts to any occasion and offers a perfect blend of elegance and comfort. Ideal for everyday wear or your next special event.
Highlights	Unspecified	3/4 sleeves, round neck, red multicolor, size 46, comfort

This case study demonstrates how targeted use of AI-supported technologies can significantly improve product data to enhance both user experience and technical discoverability. Such optimizations are essential for success in a highly competitive online market.

What is the GPT-Feedcreator?

The GPT Feed Creator is a Google Sheet powered by AppsScript and handles communication with the OpenAI interface. This tool enables users to efficiently improve and expand their product information by leveraging the advanced capabilities of OpenAI’s GPT models.

Configuration and Setup

1. API Key: First, you need an API key from OpenAI, which enables access to the AI platform.
2. OpenAI Assistant: Set up an OpenAI Assistant specifically configured for your requirements. This assistant can be fed with PDF documents describing your purchasing strategy. Creativity is key here – your own briefings, blog posts, and specific documents work well.
3. Configuration : Enter the assistant ID in the configuration sheet (“config” tab) of your Google Sheets.
4. Preparing the Shopping Feed: Prepare a CSV file with your product data, ideally using your best feed generator.
5. Setting Customer Abbreviation: Set an abbreviation for the customer to be used in the training data.
6. Adjusting the Briefing: Adjust the briefing as needed to meet the specific requirements of your feed.

Workflow

After configuration, the workflow begins by importing the CSV file using the “Import CSV” button. The product data is then displayed in the “Input Feed.” The “Improve Products” button initiates the AI-assisted optimization of the product data. The improved data appears in the sheet after a while. Products selected for the final feed are marked as “Approved.” These are then transferred to the final “output” feed using the “Process Approved” function.

Continuous Improvement and Adaptation

Continuously improving the generated product data is crucial to maximizing the effectiveness of AI integration. Regular reviews and adjustments to the AI model can continuously increase the accuracy and relevance of the data. This ensures that the product data always meets current SEO standards and is optimally optimized for Google Shopping.

For particularly successful results, you can enable the “Training” option to use this data for future improvements. Please note that this process will overwrite old training data. Automated processes can be scheduled via the script settings so that individual script functions are executed at specific times.

Disclaimer

It’s important to emphasize that the GPT-Feedcreator is a powerful, but not error-free tool. Especially at the beginning, it is advisable to closely monitor the outputs before they are adopted into the production environment.

Are Feed Generators Now Obsolete?

Given the advanced capabilities that the GPT-Feedcreator offers, one might wonder if traditional feed generators like Channable, FeedDynamix, and DataFeedWatch have now become obsolete. The answer is: Not yet. Although the GPT-Feedcreator automates the optimization and enrichment of product data, feed generators still play a crucial role in the overall process.

• Feed generators are specialized in creating and managing product feeds that are precisely tailored to the requirements of various distribution channels and platforms. They not only offer the ability to create feeds but also to efficiently manage and update them.
• GPT-Feedcreator on the other hand, is designed to optimize these feeds by improving product data based on AI-powered technologies.

Integration with Feed Generators: Optimizing Data Flow

The GPT-Feedcreator works seamlessly with feed generators like Channable to efficiently structure the data flow and ensure that only relevant product data is forwarded for optimization. This integration allows for the creation of customized feeds that are specifically tailored to the requirements of the GPT-Feedcreator. This way, even with large product catalogs, the most important products can be optimized first in a cost-effective manner.

How the Integration Works

1. Feed Creation: The feed generator (Channable, FeedDynamix, Datafeedwatch) first creates a specially adapted feed that is precisely aligned with the needs and capacities of the GPT-Feedcreator. This step is crucial to maximize the effectiveness of the entire optimization process.
2. Selection of Product Data: Only those product data that are eligible for optimization are included in the feed. This helps to save resources and make the process as efficient as possible.

Exclusion Criteria for Optimization

To determine which products should be included in the feed, specific exclusion criteria are applied. These criteria help to select products that can benefit the most from optimization. Here are some ideas on how to increase efficiency:

• Product Price: Products below a certain price level may be excluded as the effort for optimization could exceed the potential benefit.
• Sales Frequency: Products with low sales frequency might receive lower priority to concentrate resources on more frequently sold items.
• Stock Quantity: Products with low stock quantities could be excluded to focus on items with higher availability.
• Revenue: Items with low revenue contribution could also be exempted from optimization.
• Already Optimized Attributes: Products that already have optimized titles or descriptions may not need further processing and are therefore not included.

This targeted selection and pre-filtering of product data ensures that the GPT-Feedcreator focuses its capacities on the most promising candidates, thus generating maximum added value.

Efficiency and Cost-Effectiveness of the GPT-Feedcreator

The GPT-Feedcreator has revealed impressive performance data in tests and practical applications, demonstrating its effectiveness and efficiency in optimizing Google Shopping Feeds. Here are the key data points summarized:

Time Money

• Processing time: The Feedcreator takes an average of 33 seconds to improve individual product data. This is not lightning-fast but ultimately depends on the data depth and processing times of the model at OpenAI.
• Cost per product: Each product improvement costs approximately 0.16-0.25 euros, depending on the model used. It’s not free, but when compared to manual processing times, it’s still quite reasonable.

Features Benefits

• Data processing: The tool is configurable for various CSV data and supports diverse content fields, ensuring broad applicability across different industries and product ranges.
• SEO optimization: In addition to improving the product data, the GPT feed creator can also be modified without code adjustments, so that, for example, SEO optimization of the title and meta description is possible.
• Training and customization: The Feedcreator allows learning from results and continuously improving the system. By marking high-quality data as “Training,” the quality of future outputs is continuously enhanced.
• Automation: Various steps of the process can be automated, minimizing operational effort and maximizing efficiency. The ability to schedule script functions offers additional convenience for users.
• Tip for better results: For product categories that vary greatly (e.g., clothing and kitchen items), it is recommended to first generate and train individual items from each product type. For significant content differences within a category, such as pants versus shirts, train an example item for each.
• Monitoring and quality assurance: Due to the high level of automation and the tool’s strong performance, users are advised to thoroughly check the outputs, especially in the initial phase, before they go into production.

Final Consideration: Transformation of E-Commerce through AI-Driven Optimization of Google Shopping Feeds

The challenges of modern e-commerce, especially in fast-moving and niche market segments, require advanced data management and optimization solutions. The GPT Feed Creator, powered by OpenAI’s ChatGPT, offers such an innovative solution, enabling significant improvements in the quality and efficiency of Google Shopping feeds.

By automating the data creation and optimization process, online retailers can improve their product presentations, boost search engine visibility, and ultimately increase conversion rates. Integrating artificial intelligence into product data management enables more precise and engaging product descriptions that are precisely tailored to the needs of the target audience. This not only leads to a better user experience but also optimized resource utilization by minimizing manual intervention.

The advanced features of the GPT Feed Creator, including continuous improvement through training and customization, as well as the ability to automate specific processes, underscore this technology’s capacity to adapt to the constantly changing demands of the market. Initial applications have demonstrated that the Feed Creator delivers excellent results not only in theory but also in practice, increasing productivity while ensuring the quality of product data.

In conclusion, the introduction of the GPT Feed Creator to e-commerce represents a significant advancement that enables companies to successfully compete in a competitive environment. Through the targeted use of AI-driven technologies, the online retail landscape is being reshaped, resulting in a more efficient, customer-centric, and ultimately more profitable industry.