class Activity 2 : Data Mining by ghinnayatul fitrriya https://padlet.com/gynna2441/bmac3m58tf476ry8 en-us 2022-12-04 13:29:31 UTC 2025-12-23 07:12:56 UTC hello@padlet.com DATA MINING DEFINITION gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2408008445
Data mining is a logical process that is used to search through a large amounts of data in order to find useful data. The goal of this technique is to find patterns that were previously unknown. Once these patterns are found they can further be used to make certain decisions for the development of their businesses.]]> 2022-12-04 13:35:37 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2408008445 DATA MINING PROCESS gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2408010625 hree steps are involved during the data mining process

  • Exploration
  • Pattern identification 
  • Deployment
]]> 2022-12-04 13:39:54 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2408010625 DATA MINING ALGORITHMS AND TECHNIQUE gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2408021740
Knowledge discovery from databases uses a variety of methods and techniques:

i) Classification Technique

ii) Clustering Technique

iii) Regression techniques

iv) Neural networks
]]> 2022-12-04 13:58:13 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2408021740 EXAMPLE OF DATA MINING APPLICATIONS gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2408036924
i. FBTO Dutch Insurance Company (Healthcare Provider)

ii. ECtel Ltd., Israel (Cybersecurity)

iii. Provident Financial’s Home Credit Division, United Kingdom (Banking and Financial Services)

iv. Soft map Company Ltd., Tokyo (Advertising and Marketing)
]]> 2022-12-04 14:24:09 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2408036924 DATA MINING TECHNIQUES AND APPLICATIONS gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409297417 2022-12-05 15:21:03 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409297417 gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409313184
In the first step of data exploration data is cleaned and transformed into another form, and important variables and then nature of data based on the problem are determined]]> 2022-12-05 15:30:15 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409313184 gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409313974 Once data is explored, refined and defined for the specific variables the second step is to form pattern identification. Identify and choose the patterns which make the best prediction.]]> 2022-12-05 15:30:45 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409313974 gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409314207 Patterns are deployed for desired outcome.]]> 2022-12-05 15:30:53 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409314207 FBTO Dutch Insurance Company gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409325382 * Financial Analysis

Challenges:
  • To reduce direct mail costs.
  • Increase the efficiency of marketing campaigns.
  • Increase cross-selling to existing customers, using inbound channels such as the company’s sell center and the internet a one year test of the solution’s effectiveness.

Results:
  • Provided the marketing team with the ability to predict the effectiveness of its campaigns.
  • Increased the efficiency of marketing campaign creation, optimization, and execution.
  • Decreased mailing costs by 35 percent.
  • Increased conversion rates by 40 percent.
]]> 2022-12-05 15:37:14 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409325382 ECtel Ltd., Israel gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409331923 * Telecommunication Industry

Challenges:
  • Fraudulent activity in telecommunication services.

Results:
  • Significantly reduced telecommunications fraud for more than 150 telecommunication companies worldwide.
  • Saved money by enabling real-time fraud detection.
]]> 2022-12-05 15:40:55 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409331923 Provident Financial's Home Credit Division., United Kingdom gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409336269 * Finance Industry and Criminal Investigation 

Challenges:
  • No system to detect and prevent fraud.

Results:
  • Reduced frequency and magnitude of agent and customer fraud.
  • Saved money through early fraud detection.
  • Saved investigator’s time and increased prosecution rate.
]]> 2022-12-05 15:43:34 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409336269 Soft map Company Ltd., Tokyo gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409338002 * Retail Industry 

Challenges:
  • Customers had difficulty making hardware and software purchasing decisions, which was hindering online sales.

Results:
  • Page views increased 67 percent per month after the recommendation engine went live.
  • Profits tripled in 2001, as sales increased 18 percent versus the same period in the previous year.
]]> 2022-12-05 15:44:42 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409338002 gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409347822
Classification is the most commonly applied data mining technique to develop a model that can classify the population of records at large. Fraud detection and credit risk applications are particularly well suited to this type of analysis. This approach frequently employs decision tree or neural network-based classification algorithms.

Types of  classification 
  • Classification by decision tree induction  
  • Bayesian Classification  
  • Neural Networks  
  • Support Vector Machines (SVM)  
  • Classification Based on Associations
]]> 2022-12-05 15:50:30 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409347822 gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409351597
Clustering can be said as identification of similar classes of objects. By using clustering techniques we can identify dense and sparse regions in object space. Classification approach can also be used for effective means of distinguishing groups or classes of object but it becomes costly so clustering is often preferred.

Types of clustering
  • Partitioning Methods  
  • Hierarchical Agglomerative (divisive) methods 
  • Density based methods  
  • Grid-based methods  
  • Model-based methods

]]> 2022-12-05 15:52:47 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409351597 gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409381400
Regression technique can be adapted for predication while regression analysis can be used to model the relationship between one or more independent variables and dependent variables. In data mining, independent variables are attributes already known and response variables are what we want to predict. The same model types can often be used for both regression and classification.

 Types of regression methods
  •  Linear Regression  
  • Multivariate Linear Regression  
  • Nonlinear Regression  
  • Multivariate Nonlinear Regression  

]]> 2022-12-05 16:09:13 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409381400 gynna2441 https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409382205
Neural networks have the remarkable ability to derive meaning from complicated data and can be used to extract patterns and detect trends. These are well suited for continuous valued inputs and outputs. For example handwritten character reorganization, for training a computer to pronounce English, and many real world business problems.

Types of neural networks  
  • Back Propagation  

]]> 2022-12-05 16:09:43 UTC https://padlet.com/gynna2441/bmac3m58tf476ry8/wish/2409382205