Summarization Also Known As Associations

Published Date: 02 Nov 2017

introduction

. Many a times this intelegence is characterized by a kind of behavior that allows an individual to change an disruptive behavior to something more advanved behavior to something more constructive. These behaviours are many time social or personel behaviors. Thus a behavior can b adapted to something else. A human being or an animal makes decisions continuesly without any central control or coordination. Since the computer age dawned on humanity, one of the most important areas in information technology has been that of decision support. In todays real world this area is most important than ever. Today working in dynamic and ever-changing environment, modern-day managers are responsible for an assortment of effective decisions.

Adaptive business intelegence brings forward some of the important questions such as:

The workforce of the company increased or decreased?

Start up with new market interest?

Develop new products?

Invest in research and development?

To create an effective adaptive business intelegence system it should consist of three major components:

The element of making predictions such as sales price prediction.

The element for making near-optimal decisions like the proper distribution of a product.

A component for adapting the prediction module to changes in the environment.

Hence we can say Adaptive business intelligence is a set of theories, methodologies, processes, architectures for business purposes. It can handle large ammont of information to help identify send develop new opportunities. For long-term stability and market advantages, new opportunities and implementation of effective strategy is made use of. Adaptive business intelligence technologies provide historical, current and predictive views of business operations. The functions of adaptive business intelegence is same as that of competitive intelligence in today’s world. Because both the ideas work on decision making.

Self-adaptive software is one the most important discoveries in the field of Adptive business intelligence. Originally discovered as evolution strategies in Germany. Due to its Self-adaptive nature it enables the algorithm to dynamically adapt to the problem characteristics and even to cope with ever changing environmental conditions as they occur in unforeseeable ways in many real-world business applications.

Over the past 50 years, computer science has seen many number of fundamental inventions and, coming along with them, revolutions such as how software systems are able to deal with data.

50es. Von Neumann architecture, simple operating systems, most basic programming languages.

60es. Improved operating systems (especially UNIX), structured programming, object-oriented programming, functional and logic programming.

70es. Relational model of Codd, relational database management systems (RDBMS).

80es. Enterprise resource planning (ERP) systems, production planning (PPS) systems, reflecting an integrated toolbox on top of the RDBMS-level.

90es. World wide web and internet-programming, facilitating a world-wide integrating access to ERP- and PPS-systems.

Adaptive business intelligence

The methodology focuses completely on the business relevant aspects, such as the business input and output. Business input means the problem to be solved, together with the corresponding data, and business output is the problem knowledge or problem solution generated by the approach. The important tasks on the way from data and problem to an optimal business solution are data mining, data analysis and optimization tasks. For performing this tasks, computational intelligence today offers technologies which allows us to solve complex problems which was not possible in early days.

img 1.jpg

Adaptive business intelligence model

In data analysis and data mining, the task is to find out hidden knowledge from large amount of data. Like in financial applications, chemical processes, marketing data and many other fields. The term knowledge simplifies that the output should be compact, presented in a symbolic way, interpretable and highly relevant to the data. Derived knowledge and mathematical model are also used together so that the knowledge is incorporated into a model. Technologies from computational intelligence which support various aspects of data mining process includes classifier systems, genetic programming, fuzzy logic, and rough sets.

Data mining

Data mining is known as data or knowledge discovery. It is the process of studying data from different prospective and summarizing it into use full information, such research can help us to increase the output and decrease the cost and time spend on it. Data mining allows users to analyze the data from many different areas or angles, categorize it, and summarize the relationships identified. Technically, data mining is the process of finding correlations or patterns among dozens of fields in large relational database. Data mining majorly focuses on retail, financial, communication, and marketing organizations. It enables these companies to determine relationships among "internal" factors such as price, product positioning, or staff skills, and "external" factors such as economic indicators, competition, and customer demographics. And, it enables them to determine the impact on sales, customer satisfaction, and corporate profits. Finally, it enables them to "drill down" into summary information to view detail transactional data.

Untitled.jpg

Modern science and engineering are based on using first-principle models to describe physical, biological and social systems. Such approach starts with a basic scientific model, such as Newton’s law of motion or Maxwell’s equations in electromagnetism, and then builds upon them various applications in mechanical engineering or electrical engineering. Since data mining is a natural activity to be performed on large data sets, one of the largest target markets is the entire data-warehousing, data-mart, and decision-support community from the industries such as retail, manufacturing, telecommunication, health care, insurance, and transportation. In the business community, data mining technology can b used to discover new purchasing trends, plan investment strategies, and detect unauthorized expenditures in the accounting system. Data mining techniques can be applied to problems of business process reengineering, in which the goal is to understand interactions and relationships among business practices and organizations.

In simple words data mining is referd to extracting or mining knowledge from large amount of data. Mining is a vivid term characterizing the process that finds a small set of precious nuggets from a great deal of raw material. Thus , such a misnomer that carries both data and mining became a polpular choice. Many people treat data mining, as a synonym for another popularly used term, knowledge Discovery from Data, or KDD.

s.jpg

Data mining process:

Data cleaning (to remove noise and inconsistent data)

Data integration (where multiple data sources may be combined)1

Data selection(where data relevant to the analysis task are retrieved from the database)

Data transformation(where data are transformed or consolidated into forms appropriate for mining by performing summary or aggregation operations, for instance)

Data mining (an essential process where intelligent methods are applied in order to extract data patterns)

Pattern evaluation (to identify the truly interesting patterns representing knowledge based on some interestingness measures; Section 1.5)

Knowledge presentation (where visualization and knowledge representation techniques are used to present the mined knowledge to the user)

Data mining Algorithm

A data mining algorithm is a set of heuristics and calculations that creates a data mining model from data. While creating a model, the algorithm first analyzes the data provided, looking for specific types of patterns or trends (similar kind of data). The algorithm uses the results of this analysis to define the optimal parameters are then applied across the entire data set to extract actionable patterns and detailed statistics.

Data mining methods

Predictive modeling also know as classification or regression methods.

Classification and regression assign a new data record to one of several predefined categories or classes. Regression deals with predicting real-valued fields, it is also called as supervised learning.

Segmentation also known as clustering

Partition the dataset into subsets or groups such that elements of a group share a common set of properties, with high within group similarity and small inter-group similarity, it is also called as unsupervised learning.

Summarization also known as associations

Association detect sets of attributes that frequently co-occur, and rules among them. For example: 90% of the people who buy bread, also buy milk (60% of all grocery shoppers buy both)

Sequence mining

It discover sequences of events that commonly occur together. E.g.: In a set of DNA sequence ACGTC if followed by GTCA after a gap of 9, with 30% probability.

model

Simple data mining example

Find out all credit applicants with last name Smith? This is an example of Classification.

Identify customers who have purchased more than 10,000$ in last four months? This is an example of clustering.

Find all customers who have purchased milk? This is an example for association rule.

Adapting Data mining technology in business

The economics of customer relationship are changing in fundamental ways, and companies are facing the need to implement new solutions and strategies that address these changes. The concept of mass production and mass marketing, first started during the industrial revolution. The tools and technologies of data warehousing, data mining and customer relationship management (CRM) afford new opportunities for business to act on the concept of relationship marketing. Data mining tools can answer business questions that traditionally were time consuming to resolve decicion-making problems.

There are number of industries that are using data mining applications. Some of these organization include retail stores, hospitals, banks, insurance companies, manufacturing combining with data mining techniques like statistics, pattern recognition and other important tools used to find patterns and combinations which are difficult to find in real world.

Retail Marketing

The use of store-branded credit cards and point-of-sale systems, retailers can keep record of every shopping transactions. This enables to better understand various customer segments. Some retail applications include performing basket analysis also known as affinity analysis, basket analysis reveals which product is cosutomer tends to purchase together. This knowledge can improve stocking, store layout strategies and promotions.

Sale forecasting – examining time based patterns helps retailer make stocking decisions. If a customer purchases an item, then whats the time prediction for purchasing the complementary item for that product.

Database marketing – retailers can develop profile of customers with certain behaviors, for example, those who purchase designer labels clothing or those people who attend sales. This information can be used to focus cost-effective promotions.

Merchandise planning and allocation – when retailers add new stores, they can improve merchandise planning and alloction by examining patterns in store with similar characteristics. Retailer can also use data mining to determine the ideal layout for a specific store.

Banking sector

Banks can utilize knowledge discovery for various applications such as,

Card marketing – by identifying customer segments, card applicants and acquires can improve profitability with more effective acquisition and retention programs, targeted product development and customized pricing.

Cardholder pricing and profitability – card applicants