It is the process that comprises of searching, collecting, filtering and analyzing data. It is the process which turns raw data into essential information. It is related to finding unexpected connections among the data mined. Data mining is mostly used while working with huge data sets. Data mining is also called as Knowledge discovery, Knowledge extraction, data/pattern analysis, information harvesting, etc.

APPLICATIONS OF DATA MINING:

1. Healthcare:

Using data mining in the healthcare industry will cater to more patient centered services. It will also cut down the cost and will advance the operating efficiency at the same time sustaining high quality care and this will result into patient satisfaction. Number of patients in each section can be successfully predicted by the use of data mining.

2. Market Basket Analysis:

Market Basket Analysis is used by retailers. It helps them to figure out customer purchasing pattern. Market Basket Analysis is the modelling technique which let the retailer know the probability of a customer’s buying capacity to further suggest more probable choices available. This further assists the retailer to know about customer’s needs and alter the store’s layout accordingly.

3. Education:

Use of data mining in the field of education is also known as EDM (Educational Data Mining). It can be used to maintain accurate records about the students. It also aids in providing better learning experience by analysing their future learning behavior. It can also be used for enhancing the way of teaching.

4. Fraud Detection:

Fraud detection process were considered to be time consuming but after the use of data mining it has become easier and less time consuming. As data mining turns data into information, it helps to analyse the given set of data and classify them as fraudulent or non-fraudulent. This processed data is then converted into readable records.

5. Intrusion Detection:

Intrusion can be explained as an action that can be a threat for a system and can affect confidentiality and integrity of the system. Use of data mining in intrusion detection is constructive as it adds a level of focus towards anomaly detection, which results into making intrusion detection easier and faster. It also assists in extracting data which is more relevant to the issue.

6. Financial Banking:

With evolution in technology, every sector is becoming digitalized, banking sector being one of them. Computerized banking leads to lots of new transactions. With such a huge amount of data everyday it is not possible for an individual to keep track of the records manually. Data mining not only helps them to keep track of the record but also assists them to solve business problems in banking and finance by finding pattern algorithms. This data can be used for better segmenting, targeting, accessing and retaining a gainful client.

DATA MINING TECHNIQUES:

1. Clustering:

Clustering is a data mining technique which segregates data points into groups. The data points are classified into groups based on their similarities. In this segregation, partitioning of data is done into classes. The data in a particular class is more similar to each other as compared to data present in other classes.

2. Classification:

Classification is a data mining technique which accredits items in a compilation to target categories and classes. It allocates the cases to a specific class based on their behavior. A sample model is created to classify the cases whose category is unknown into classes based on their behavior. Various algorithms can also be used for the same.

3. Association:

The association technique in data mining is used to identify the items that are related with each other. If the set of data is given, then association technique is used to find frequent patterns and correlations from the data sets.

4. Prediction:

Prediction in data mining technique is used to get values of a variable. In this technique the value of a variable can be predicted if the value of another variable is provided.

The selection of a good model is difficult if there are many numbers of predictors.

5. Text Mining:

Text mining is a data mining technique which analyses texts of a particular statement. It keeps track of occurrence of the words in a given statement. It helps to find out which word has occurred the most. It results into high quality information.

ADVANTAGES

1. Actual data is shown as outcome which results in avoiding future problems.

2. Once vital information is generated data mining helps in strategic planning.

3. Unexpected Information in results is also discovered by using data mining.

4. Data mining provides us with results which are easy to understand.

5. Complex data sets are also sorted easily with the use of data mining techniques.

6. Individuals not having any prior computer knowledge can also easily understand the results generated by using data mining techniques.

7. Using data mining reduces the costs and enhances business.

DISADVANTAGES

1. Sorting data sets is important to collect data first, which is sometimes difficult, if there are large sets of information to be retrieved.

2. Security of data is one of the major concern. Lack of proper security system can hamper the confidentiality of data.

3. In case if the collected data is not appropriate, then the result which is generated will not be beneficial and it could change the outcome of the decision making process.

CONCLUSION:

As technology is developing and every sector is being digitalized, huge amounts of data is generated. Data mining will assist us to sort that data without consuming much time and cost. There are various techniques available in data mining which will help us sort data in proper manner and result into appropriate output.