NTT Inc and NTT Docomo have utilised generative AI technology in the development a large action model (LAM). This new model enables highly personalised 1-to-1 marketing to be tailored to a customer’s needs, with the aim of improving telemarketing order rates.
During development, led by NTT, the LAM pre-learned patterns in behavioural sequences from customer time-series data to predict customers’ intent, the companies explained in a statement. The model was designed to flexibly accommodate diverse promotional strategies.
NTT explained the technology has an architecture similar to large language models and enables future behaviour prediction with a transformer-based model, a type of neural network architecture that converts an input sequence into an output sequence.
Docomo integrated customer data collected from various customer touch-points, including online channels and physical stores, into a 4W1H (Who, When, Where, What and How) format. It then built the LAM and verified the effectiveness of promotional measures.
The pair claim personalised promotional initiatives increased telemarketing orders for mobile and smart life-related services by up to two-times compared with conventional methods.
Docomo noted using innovations in design and parameter optimisation, its proprietary LAM was built using less than one day of computation, equivalent to approximately 145 GPU hours, on a GPU server equipped with eight Nvidia A100 (40GB) units.
Source: Mobile World Live
Image Credit: Stock Image
