Auto-classification uses two machine-learning methods, supervised classification and unsupervised classification, for two different purposes.
Supervised classification
Machine learning via supervised classification uses exemplars of known document types to classify new documents in a two-step process:
1 Train the algorithm using known, manually classified content.
2 Classify new content using the trained algorithm.
In a stable content environment, AI teams use supervised classification to set custom classification models specific to a particular application or organization. This method requires human intervention to select the training data and optimize the model, and thus requires substantial involvement and effort in the early phases of the project, but yields predictable, accurate results.
Unsupervised classification
Machine learning via unsupervised classification uses clustering and association algorithms to discover relationships in a heterogeneous dataset:
Clustering algorithms identify commonalities in the data, such as textual content or data format, and extrapolate relationships to create natural groupings and detect anomalous elements, such as security threats or medical issues.
Association algorithms reveal interesting relationships in the data to answer questions to address issues such as reducing customer churn or selecting related products for a promotion.
AI teams use unsupervised classification when attempting to answer these types of questions:
Is there any evidence of fraud in these financial transactions?
Are there any network performance symptoms that indicate a latent issue that would increase the risk of network failure?
Are there any anomalies in customer activity that point to possible buying trends?
Predictive analysis
Predictive analysis uses data mining, machine learning, and predictive modeling to process transactional and historical data to identify trends that indicate areas of increased risk or reward.
Specifically, predictive modelling software uses known results from existing data to train the model to predict relationships and outcomes that are likely to occur in future data and recommend a course of action. It is a business function, not a math problem or a science exercise.
AI teams use predictive analytics when attempting to answer these types of questions:
Will my customer purchase product X?
Will my customer like a recommended song?
Which of my customers are likely to switch to a competitor or cancel their contract?
Of all recently submitted claims, which ones are likely to require an additional fraud investigation unit review?
Is this applicant likely to default on their car loan in the future?
For example, predictive analytics can spot buying trends and patterns, but it takes someone with an understanding of the market to help the software interpret them and assess their relevance.
Predictive analysis is used in a wide range of markets:
Manufacturing and logistics operations apply predictive maintenance to ensure maximum performance and uptime for their assets.
Financial services and retail organizations use predictive analytics tools for many key business functions, including personalized marketing and fraud detection.
Deep learning
Deep learning techniques mimic the brain’s neuron activities, which is why they are also referred to as neural networks. Some common applications include natural-language processing, image recognition, and realistic photo and video generation. Table 1-4 shows the relationship among artificial intelligence, machine learning, and deep learning.
TABLE 1-4 Artificial Intelligence, Machine Learning, and Deep Learning
| Technique | Description | Example |
| Artificial Intelligence | Computing systems capable of performing tasks that humans are very good at | Recognize objects, recognize and make sense of speech, self-driving cars |
| Machine Learning | Field of AI that learns from historical data toward an end goal or outcome | Predict customers likely to churn |
| Deep Learning | Powerful set of machine-learning techniques that mimic the brain’s neuron activities | Computer vision, colorize photos, deep fakes, mastering a game |
Sentiment analysis
Sentiment analysis uses text mining, NLP, and other AI techniques to detect the opinions and emotions of a person based on written or spoken content, such as social media posts, reviews, videos, and podcasts. It identifies the person expressing the opinion, what the person is talking about, and whether the opinion is positive or negative.
Also called opinion mining, sentiment analysis is often used to process reviews or survey results to discern the voice of the customer and adjust a policy, product, or response accordingly.
In the early days of Twitter, many corporate social media teams would auto-retweet any content that tagged the brand. The resulting retweets of complaints of bad service were a great source of amusement to the general populace but did little to build the value of the brand. Sentiment analysis not only avoids such embarrassing moments, but also creates an opportunity to be proactive in engaging customers with knowledge and empathy.
Chapter 2
Looking at Uses for Practical AI
IN THIS CHAPTER
