MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems
This addresses the costly manual annotation and data collection for industry classification in public and corporate databases, though it appears incremental as it builds on existing multimodal resources.
The paper tackles the problem of automating industry classification for businesses by introducing MONETA, a multimodal benchmark using text and geospatial data, achieving up to 22.80% improvement over baselines with methods like multi-turn design.
Industry classification schemes are integral parts of public and corporate databases as they classify businesses based on economic activity. Due to the size of the company registers, manual annotation is costly, and fine-tuning models with every update in industry classification schemes requires significant data collection. We replicate the manual expert verification by using existing or easily retrievable multimodal resources for industry classification. We present MONETA, the first multimodal industry classification benchmark with text (Website, Wikipedia, Wikidata) and geospatial sources (OpenStreetMap and satellite imagery). Our dataset enlists 1,000 businesses in Europe with 20 economic activity labels according to EU guidelines (NACE). Our training-free baseline reaches 62.10% and 74.10% with open and closed-source Multimodal Large Language Models (MLLM). We observe an increase of up to 22.80% with the combination of multi-turn design, context enrichment, and classification explanations. We will release our dataset and the enhanced guidelines.