Solving Business Problems with Oracle Gegevens Mining
This tutorial shows you how to use Oracle Gegevens Mining to solve business problems.
Time to Accomplish
Approximately Two hours
This tutorial covers the following topics:
Place the cursor overheen this icon to flow and view all the screenshots for this tutorial. (Caution: This activity fountains all screenshots at the same time, so response time may be slow depending on your Internet connection.)
Note: Alternatively, you can place the cursor overheen an individual icon ter the following steps to fountain and view only the screenshot associated with that step. You can hide an individual screenshot by clicking it.
Gegevens Mining is sometimes called Skill Discovery-its objective is to provide actionable information, not found by other means. This information can improve the functioning of your business. For example, suppose a marketing campaign results te a 2% positive response. If Gegevens Mining can help concentrate the campaign on the people most likely to react, resulting te a 3% response, then the business outcome is a 50% increase ter revenue.
Gegevens Mining can be divided into two types of ",Learning",.
Oracle Gegevens Mining (ODM) is powerful gegevens mining software embedded ter the Oracle Database that enables you to detect fresh insights hidden te your gegevens. Oracle Gegevens Mining helps businesses to target their best customers, find and prevent fraud, detect the most influential attributes that affect Key Voorstelling Indicators (KPIs), and find valuable fresh information hidden te the gegevens. Oracle Gegevens Mining helps technical professionals find patterns te their gegevens, identify key attributes, detect fresh clusters and associations, and uncover valuable insights.
Oracle Gegevens Mining enables companies to:
Oracle Gegevens Mining enables you to go beyond standard query and reporting contraptions and Online Analytical Processing (OLAP). Query and reporting and OLAP instruments can tell you who are your top customers, what products have sold the most, and where you are incurring the highest costs. With Oracle Gegevens Mining, you can implement strategies to:
Identify likely targets and promising leads te drug discovery
Traditional business intelligence (Bisexual) devices such spil reports, interactive query and reporting, and Online Analytical Processing (OLAP), only report on what has happened ter the past. Oracle Gegevens Mining (ODM) permits you to go beyond traditional Bisexual and reporting to mine your gegevens and build advanced gegevens mining applications. ODM enables you to detect fresh insights, segments and associations, make more accurate predictions, find the variables that most influence your business, and ter general, samenvatting more information from your gegevens. For example, by analyzing the profiles of your best customers, ODM enables you to build gegevens mining models and integrated applications to identify customers who are likely to become your best customers ter the future. Thesis customers may not represent your most valuable customers today, but may match profiles of your current best customers. Moreover, with ODM you can do more and convert a predictive monster into a regular production application that distributes lists of your most promising customers to your Sales force every Monday morning. Knowing the ,strategic value, of your customers , which are likely to become profitable customers ter the future and which are not, or predicting which customers are likely to churn or likely to react to a marketing opoffering , and integrating this information into your operations is the key to proactively managing your business.
The phases of solving a business problem using Oracle Gegevens Mining are spil goes after:
Gegevens Acquisition and Prep
Note: This tutorial is not intended spil a comprehensive course on Oracle Gegevens Mining. It illustrates the technics required to carry out some common gegevens mining operations. If you want more background information about some of the topics, see the Oracle Gegevens Mining Concepts Guide.
An electronics store chain wants to distribute a discount card to its customers, but only to those customers who are expected to increase their buying (and thus the company,s revenue) because of this card. A test campaign wasgoed run on a sample of customers and the results were compiled into a table containing the customer demographics, purchasing patterns, and a measure of revenue produced by each customer.
A dataset describing the customers and results te the test campaign is used to create a monster that can be applied to all customers for the purpose of predicting revenue levels expected from each customer who uses a discount affinity card , the Target attribute to be predicted is AFFINITY_CARD with values 0 (= low revenue) and 1 (= high revenue). The distinct target values (0 and 1 ter this case) are sometimes called the target ,classes,, thus the prediction of a target value for each customer is called Classification.