AI Based Agent Modeling for Improving Business Decisions

What is Agent Based Modeling (ABM)?

Agent-based Modeling 1 is an effective simulation modeling process to be used in different types of applications including real world business problems. Agent-based modeling (ABM) is a collection of autonomous decision making entities, also called agents, and defining a relation between them. Each agent individually assesses its situation and makes decisions on the basis of a set of rules. Agents may execute various behaviors appropriate for the system they represent like producing or selling. Repetitive and competitive interactions between agents are a feature of agent-based modeling. A wide range of AI tools such as neural networks, machine learning techniques and evolutionary algorithms are used in agent based application to parse information. Thus AI-based Agent model offers a real-time application which beneficial for every industry. Its flexible implementation is an underlying reason for its popularity.

Benefits of Agent-Based Modeling  

Agent-Based Modeling captures the complex network of interactions and connections that make up real systems and make it possible to see emergent patterns and unexpected changes and events.

  • ABM gives insights into causes of emergent phenomena

Emergent phenomena result from the interactions of individual entities. For example, people behavior during a stampede, fire on a production shop floor, pipe line burst in a processing industry, electric short-circuit in a corporate office building or a traffic jam.

  • ABM uses a natural description of a business

ABM makes the model seem closer to reality. ABM also makes it possible to realize the full potential of the data a company may have about its customers. For example, it is more natural to describe how their customers react to a discount offer.

  • ABM provides a framework for testing strategy 

ABM provides a flexible framework for answering questions like why is this happening, what if these trends continue, what will happen next, what is the best that can happen. 

Application areas of ABM in Telecom Industry

ABM’s emergent phenomenon has become progressively accepted tool to predict difficult and counterintuitive situations in various moments. In telecom, customer loyalty is by no means assured.  Customer retention2 is a critical concern for mobile network operators because of the increasing competition in the mobile services sector. Such unease has driven telecom companies to exploit data as an avenue to better understand changing customer behavior. However, the effectiveness of the traditional techniques such as data-mining techniques such as clustering and classification to better understand customer retention has become debatable due to the constant change and increasing complexity of the mobile market itself.

Customer analytics and insight tools are being used to predict customer behavior, to identify the best tactics to improve retention rates by Telcos.  For instance, Vodafone3 compiles comprehensive customer profiles using data from a wide range of communication channels, including online, paid ads, and owned media. They then use Artificial Intelligence to identify the customers who are most likely to churn. Armed with this data, Vodafone matches customers with the most relevant retention plans, offering discounts to some and perks from partner companies to others. Word of mouth between customers is also explored as a possible influence factor. Importantly, methods for automating data-driven agent-based simulation model generation will support faster exploration and experimentation – including with those determinants from a wider market or social context.


ABM helps develop an improved platform to discover influence on customer churn and offer better strategies for customer retention. ABM is more than a simulation tool.  ABM helps to reduce operational risk and to develop ideas for building or rebuilding the organization strategies.

Learners’ Opportunity

ABM can be applied for everyday business solutions. For instance, through simulated actions and interactions of agents we can understand the behavior of a highly complex marketing phenomenon.  To know more, check out @

Discussion Question

Based on Vodafone use of AI in increasing customer relations, can you suggest similar uses for a retail industry?

Key words


Source Articles

  1. Mohammed Hassouna, 2012, Agent based modeling and simulation……….
  2. Chidozie Mgbemena, 21 September 2016, A Data-driven Methodology for Agent Based Exploration of Customer Retention.
  3. Andrew Mort,, Apr 20,2020, Customer Retention Strategies in the Telecom Industry.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Related Post