Enterprise AI For Dummies. Zachary Jarvinen

Enterprise AI For Dummies - Zachary Jarvinen


Скачать книгу
error-prone tasks such as classifying information for storage and retrieval or answering a question. In a world where the amount of information stored digitally is expected to double every two years well into the next decade, auto-classification makes the difference between using that information and being overwhelmed by it.

      Auto-classification uses two machine-learning methods, supervised classification and unsupervised classification, for two different purposes.

      Supervised classification

      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.

       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?

      

Because predictive analytics delivers actionable insight, in-depth knowledge in the business domain is as important as an understanding of the various analytics techniques or the ability to code analytics solutions.

      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

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

      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.

      Looking at Uses for Practical AI

      IN THIS CHAPTER

      

Reviewing the first recognizable manifestations of AI and the latest incarnations

      

Differentiating between pure AI and practical AI

      

Exploring
Скачать книгу