 What is Next Best Action? Who does not sometimes wish for a mentor who always has an appropriate advice? In general, humans are very good at rating known situations and making the right decisions, but in case of new circumstances or a huge amount of aspects to consider, good advice is priceless. In marketing and similarly in fundraising, one-on-one support is very effective, but not possible in most cases. As companies and organizations were growing, mass marketing became the state of the art, trying to sell as many items to as many customers as possible. Customer received overwhelming amounts of advertisement and offers, which can be described as a “content shock”. Since the rise of machine learning and the possibility for sophisticated data analysis, companies try to stand out by putting the customer in the center. This is done by trying to predict what the customer wants and needs. New technologies should advise marketing specialists what to do next in order to satisfy every customer individually – supported by enormous amounts of data. This concept is called Next Best Action (NBA) or Next Best Offer (NBO) and can evolve into a useful fortuneteller in case of effective implementation. The benefits of the concept are reduced advertisement cost and increased customer loyalty. How can NBA systems be developed? The goal, structure and architecture of a NBA system strongly depends on the environment and purpose it is used for. Questions to answer before the development are for example:
After goals and actions are defined, the general structure of a NBA system can be summarized as follows:  Structure of a NBA system: Actions are presented as letters; colors illustrate different categories of actions. Source: https://databasedmarketing.medium.com/next-best-action-framework-47dca47873a3 The process of step one - filter- is rather rule based, depending on what actions or offers make sense for a customer. For instance, there might be products, which cannot be offered more than one time and therefore their offer will be excluded from the action list after purchase. The same applies for the third step: Typically, the actions with the highest benefit should be chosen but it depends on the user of the system, whether more than one action is taken or the actions need to be filtered again. A reason for a second filtering step could be that only one single action of a certain category is chosen even though two actions from the same category show very high benefit values. As it turns out, most NBA systems are based on proven business rules and requires a well-defined framework before the most complex component – the rating of the actions - can be developed.
A rule-based system requires a lot of experience in the domain and takes time to develop because it is all done by hand: Rule like “rate action xy high if the customer already bought from the category ab in the last two years” can be data driven if they are based on previous findings. Most companies already use such business rules for marketing. The scoring does not need to be metric (with numbers), as shown in the picture below. The system is not adaptive and needs to be adjusted, if the circumstances change. Rule-based systems are characterized by extreme simplification, since the real, very complex interrelationships cannot be completely cast into rules. The needs and the reactions of a customer will change depending on the previous action, which is very difficult to represent in a rule-based way.  Example for a rule based system. Experience and detailed development is needed to incorporate sufficient rules If a low or intermediate level of machine learning is considered, relatively simple scores and predictions can be incorporated into the system. The simplest approach would be to calculate the probability for all customers to react positively to an action (propensity). To just predict which action might provoke a positive reaction might not be suitable for predicting long term customer loyalty. Several scores and probabilities can be combined to achieve this goal. For example, the propensity can be combined with a prediction of long term customer engagement. The reason for this is that on one hand no action is useful if the customer does not like the action (propensity), but on the other hand the actions also need to have a benefit for the organization (prediction of customer engagement/success for the organization). The scores can be weighted according to their importance and any number of further adjustments can be made. Typically, such a system will still be embedded in several predefined rules. Similar like factors for weighing scores (by multiplication), a higher importance of a score can be expressed by adding meaningful numbers to the score. Disadvantages are that still a lot of experience in the field of use is needed. Scores are required for all actions and they need to indicate the benefit or propensity to the same extent. The system could automatically adjust to a certain extend if the scores themselves are linked to current data and regularly monitored.  Full Deep Learning Models require more abilities that are technical, experience with deep learning and an appropriate technical environment. The difference to the previous systems is that these models are black box-models without the necessity for the users to tweak and define the rules and scores themselves. While intermediate levels of machine learning require a programmer to intervene to make adjustments, in deep learning the algorithms themselves determine whether their decisions are right or wrong. Internally, the algorithm will calculate scores for each action but will determine the best calculation and weighing itself. Rating systems in this category can range from a deep neural network for predicting benefits of actions to reinforcement learning models, which do not need a lot of training data in advance but can learn implicit mechanisms by trial and error. As long as these systems are fed with current data, they are adaptable. Disadvantages of this approach are the complex development and reduced interpretability due to the fully automated process.  Fully automated deep learning model. So What?
In our view, George Box´ good old quote “All models are wrong, but some are useful” is also worth considering in the context of NBA models. Whether and how these approaches suit the needs of respective (nonprofit) organizations should be evaluated holistically. If you are interested in getting to know more about the concept of NBA or even think about implementing it in your SOS association, please do not hesitate to get in touch with us. Sources https://www.altexsoft.com/blog/next-best-action-marketing-machine-learning https://databasedmarketing.medium.com/next-best-action-framework-47dca47873a3 https://medium.com/ft-product-technology/how-we-calculate-the-next-best-action-for-ft-readers-30e059d94aba https://www.mycustomer.com/marketing/strategy/opinion-five-rules-for-the-next-best-offer-in-marketing
0 Comments
Leave a Reply. |
