PoC creation

The Brightgrove team was fully responsible for the E2E creation of a PoC to help the client identify if the offered

technical solution could cover his business requirements. This PoC involved the following phases:

• Focus on core functionality validation

• Use managed services to reduce operational overhead

• Implement basic monitoring

• Limited but functional error handling

Taxonomy and categories implementation

We developed an AI-powered solution that analyzes product data, identifies trends, and provides recommendations to optimize listings and boost sales. For instance, if a seller offers black 0.5L water bottles, the system analyzes similar products across marketplaces, identifies trends in consumer preferences, and might recommend optimizing to green 0.75L bottles based on market data and customer sentiment analysis.

For the PoC and further development, we needed to research language models capable of encoding text data—product descriptions and other metadata—to taxonomy representation.

We needed to evaluate various language models by several criteria:

• Model size

• Performance

• Easy to adapt to new data (fine-tuning)

In the case of the PoC, light models like tiny-GPT or tiny-BERT were used for a more limited number of categories. For the implementation of image-to-text (taxonomy) encoding, we needed an engine capable of searching similar media based on their semantics rather than visual features. With a stable image similarity search engine, the system can analyze new image data from an existing annotated image database and collect taxonomy tags from similar media.

Taxonomy tags will be aggregated based on the similarity score, and the taxonomy data will be generated automatically for new images.

Product deployment and further development

The system leverages advanced machine learning to generate visual suggestions for product improvements, optimal keyword combinations, and pricing strategies.