Machine Learning Functions
Machine learning problems are categorized into mining functions. Each machine learning function specifies a class of problems that can be modeled and solved. Machine learning functions fall generally into two categories - supervised and unsupervised. Notions of supervised and unsupervised learning are derived from the science of machine learning, which is a sub-area of data science.
Algorithms
An algorithm is a mathematical procedure for solving a specific kind of problem. For some machine learning techniques, you can choose among several algorithms.
Each algorithm produces a specific type of model, with different characteristics. Some machine learning problems can best be solved by using more than one algorithm in combination. For example, you might first use a feature extraction model to create an optimized set of predictors, then a classification model to make a prediction on the results.
Supervised Learning
Supervised learning is also known as directed learning. The learning process is directed by a previously known dependent attribute or target.
Supervised machine learning attempts to explain the behavior of the target as a function of a set of independent attributes or predictors. Supervised learning generally results in predictive models.
The building of a supervised model involves training, a process whereby the software analyzes many cases where the target value is already known. In the training process, the model "learns" the patterns in the data that enable making predictions. For example, a model that seeks to identify the customers who are likely to respond to a promotion must be trained by analyzing the characteristics of many customers who are known to have responded or not responded to a promotion in the past.
Oracle Machine Learning supports the following supervised machine learning functions:
Table 1-1 Supervised Machine Learning Functions
| Function | Description | Sample Problem | Supported Algorithms |
|---|---|---|---|
| Feature Selection or Attribute Importance | Identifies the attributes that are most important in predicting a target attribute | Given customer response to an affinity card program, find the most significant predictors | |
| Classification | Assigns items to discrete classes and predicts the class to which an item belongs | Given demographic data about a set of customers, predict customer response to an affinity card program | |
| Regression | Approximates and forecasts continuous values | Given demographic and purchasing data about a set of customers, predict customers' age | |
| Ranking | Predicts the probability of one item over other items | Recommend products to online customers based on their browsing history | XGBoost |
| Time Series | Forecasts target value based on known history of target values taken at equally spaced points in time | Predict the length of the ocean waves, address tactical issues such as projecting costs, inventory requirements and customer satisfaction, and so on. | Exponential Smoothing |
Unsupervised Learning
Unsupervised learning is non-directed. There is no distinction between dependent and independent attributes. There is no previously-known result to guide the algorithm in building the model.
Unsupervised learning can be used for descriptive purposes. In unsupervised learning, the goal is pattern detection. It can also be used to make predictions.
Oracle Machine Learning supports the following unsupervised machine learning functions:
Table 1-2 Unsupervised Machine Learning Functions
| Function | Description | Sample Problem | Supported Algorithms |
|---|---|---|---|
| Anomaly Detection | Identifies rows (cases, examples) that do not satisfy the characteristics of "normal" data | Given demographic data about a set of customers, identify which customer purchasing behaviors are unusual in the dataset, which may be indicative of fraud. | |
| Association | Finds items that tend to co-occur in the data and specifies the rules that govern their co-occurrence | Find the items that tend to be purchased together and specify their relationship | Apriori |
| Clustering | Finds natural groupings in the data | Segment demographic data into clusters and rank the probability that an individual belongs to a given cluster | |
| Feature Extraction | Creates new attributes (features) using linear combinations of the original attributes | Given demographic data about a set of customers, transform the original attributes into fewer new attributes. | |
| Row Importance | Row importance technique is used in dimensionality reduction of large data sets. Row importance identifies the most influential rows of the data set. | Given a data set, select rows that meet a minimum importance value prior to model building. | cur Matrix Decomposition |