A multinational company’s customer analytics initiative reveals unexpected patterns not defined in the business objectives. The AI team explains that…

The scenario describes Unsupervised Learning. This approach is used to find hidden patterns, anomalies, or structures in data without predefined labels or target outcomes. The key indicators are the discovery of "unexpected patterns not defined in the business objectives" and the generation of insights from "observed data relationships." The AI is not predicting a specific, known target but is exploring the data to reveal inherent groupings or correlations, which is the core function of unsupervised techniques like clustering or association rule mining.

A. Supervised Learning: This requires labeled data to train a model to predict specific, predefined outcomes (e.g., classifying customers as "likely to churn").

C. Reinforcement Learning: This involves an agent learning to make decisions by taking actions in an environment to maximize a cumulative reward, which is not described here.

D. Deep Learning: This is a subfield of machine learning using neural networks with many layers; it can be supervised, unsupervised, or reinforcement-based, but is not the learning type.

1. Ng, A. (n.d.). CS229 Machine Learning Course Materials. Stanford University. Retrieved from http://cs229.stanford.edu/notes2022fall/cs229-notes1.pdf (Section 1 provides a clear definition and distinction between supervised and unsupervised learning).

2. Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer. (Chapter 1, Section 1.1, introduces the three main types of machine learning problems, defining unsupervised learning as discovering groups of similar examples within data).

3. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. (Chapter 5, Section 5.1.3, distinguishes between supervised and unsupervised learning algorithms).