Question
A financial institution has noisy, missing and inconsistent customer data. Explain suitable data preprocessing techniques including cleaning, integration, transformation, reduction and discretization before mining.
Answer :
Word Count : 591
______ ____ ____ _________ ____ _____ _______ _____ ______.
_____ _____ __________ _______ ______ _______.
_________ _______ __________ ______ ____ _________ ____ __________.
__________ _________ ___ ___ ________ __________ ______ ______.
____ ___ __________ ___ ______ _____ ______ _________ ___.
__________ _________ _______ ______ _______ ________ ________ ________ ______ ________ ____ __________.
__________ _________ ______ _____ ______ _____ _________ ________ _________ ___.
______ ____ _______ __________ _________ __________ ____ ___ ____ __________ ____ _____.
________ _____ _______ _________ _____ _______ ___.
_____ ________ _____ _______ ________ ______ _______ _____ _______ ________ ________.
_________ _______ __________ ____ ______ ___ ___ _____ _______.
_______ ____ ___ _________ ________.
_________ ____ _________ _________ _________ __________ ____ _______ ________.
______ _________ ________ ___ ______ __________ ______ __________.
___ __________ _____ ______ __________ _________ ____ ____.
_______ ___ ____ _____ _________ _______ ________ ____ _______.
___ _____ ______ ______ _____ _______ _______.
______ ______ _______ _____ ____ __________ ____ ______.
________ ____ ____ ___ _________ ____ ______ ___ ________.
________ _______ ____ ______ ____ ___ _________ __________ ________ _______ ______ _____.
_________ ________ _________ _____ ____ _____ ______ ____ ______.
_______ _______ __________ ________ _______.
__________ ________ ________ ______ ___ ______.
________ _________ _______ ___ ___ _____ _________ ______ ________ _________.
____ __________ __________ ____ ____ ________ ______.
__________ ______ _____ ______ ________.
_______ ______ __________ ___ ______ ___ _________ ____ _____ ___ _____ ______.
_________ ___ ____ _______ __________ ___ ________ ______ ___ ____ _________ ___.
________ __________ ________ __________ _________ ________ ___.
_________ ______ ______ __________ ____ _______ ________ __________ ____ ___.
____ ________ __________ _____ ___ ________.
__________ ___ ____ ___ ____ _____ ________ ___.
_______ ___ _________ _____ __________ ________ ___ ____ __________ _____.
__________ _______ ______ __________ ________ __________ ______ __________ ______ __________ _________.
_______ _________ _______ ___ _________ _________ _________ _______.
___ _____ __________ _____ ____ ___ ____ _______ _____ ______ ____ ____.
_____ ________ ______ _________ __________ _________ ________ ____.
____ _____ ________ _____ _________ ________.
___ ____ ____ ______ ________ ___ _____ ____ ______ ___.
____ _______ ______ _________ ___ ________ ___.
_________ ________ __________ _______ ______ ________ ___.
_______ _____ _____ _______ ________ ____ ______ ____.
_____ ________ ________ ______ __________ ________ _______ __________ _________ _________.
_____ ____ ___ _________ ______ ___ _______ _____.
___ _________ ________ ______ _____.
________ _________.
Skip in 10
Data preprocessing is a fundamental step in data warehousing and data mining because the quality of mining results depends directly on the quality of the input data. A financial institution often collects customer information from multiple sources such as bank branches, online banking platforms, mobile applications, credit card systems, insurance records, and loan management systems. Such data frequently contains noise, missing values, inconsistencies, duplicates, and redundant attributes. Before applying mining algorithms for fraud detection, customer segmentation, credit risk analysis, or loan approval, appropriate preprocessing techniques must be applied. Data cleaning is the first and most important preprocessing step. It aims to detect and correct errors in the dataset. Missing values in customer information, such as income, address, occupation, or contact details, may occur because of incomplete forms or system failures. These missing values can be handled by ignoring records with excessive missing information, replacing missing values with a global constant, filling them with the attribute mean or median, or estimating them using predictive methods such as regression or classification. Noisy data, such as incorrect account balances, typing errors, or abnormal transaction values, can be smoothed using binning, clustering, regression, or outlier detection techniques. Duplicate customer
__________ _______ _____ _______ _______ ___ ________ ____ ______ __________ ____.______ ____ ____ _________ ____ _____ _______ _____ ______.
_____ _____ __________ _______ ______ _______.
_________ _______ __________ ______ ____ _________ ____ __________.
__________ _________ ___ ___ ________ __________ ______ ______.
____ ___ __________ ___ ______ _____ ______ _________ ___.
__________ _________ _______ ______ _______ ________ ________ ________ ______ ________ ____ __________.
__________ _________ ______ _____ ______ _____ _________ ________ _________ ___.
______ ____ _______ __________ _________ __________ ____ ___ ____ __________ ____ _____.
________ _____ _______ _________ _____ _______ ___.
_____ ________ _____ _______ ________ ______ _______ _____ _______ ________ ________.
_________ _______ __________ ____ ______ ___ ___ _____ _______.
_______ ____ ___ _________ ________.
_________ ____ _________ _________ _________ __________ ____ _______ ________.
______ _________ ________ ___ ______ __________ ______ __________.
___ __________ _____ ______ __________ _________ ____ ____.
_______ ___ ____ _____ _________ _______ ________ ____ _______.
___ _____ ______ ______ _____ _______ _______.
______ ______ _______ _____ ____ __________ ____ ______.
________ ____ ____ ___ _________ ____ ______ ___ ________.
________ _______ ____ ______ ____ ___ _________ __________ ________ _______ ______ _____.
_________ ________ _________ _____ ____ _____ ______ ____ ______.
_______ _______ __________ ________ _______.
__________ ________ ________ ______ ___ ______.
________ _________ _______ ___ ___ _____ _________ ______ ________ _________.
____ __________ __________ ____ ____ ________ ______.
__________ ______ _____ ______ ________.
_______ ______ __________ ___ ______ ___ _________ ____ _____ ___ _____ ______.
_________ ___ ____ _______ __________ ___ ________ ______ ___ ____ _________ ___.
________ __________ ________ __________ _________ ________ ___.
_________ ______ ______ __________ ____ _______ ________ __________ ____ ___.
____ ________ __________ _____ ___ ________.
__________ ___ ____ ___ ____ _____ ________ ___.
_______ ___ _________ _____ __________ ________ ___ ____ __________ _____.
__________ _______ ______ __________ ________ __________ ______ __________ ______ __________ _________.
_______ _________ _______ ___ _________ _________ _________ _______.
___ _____ __________ _____ ____ ___ ____ _______ _____ ______ ____ ____.
_____ ________ ______ _________ __________ _________ ________ ____.
____ _____ ________ _____ _________ ________.
___ ____ ____ ______ ________ ___ _____ ____ ______ ___.
____ _______ ______ _________ ___ ________ ___.
_________ ________ __________ _______ ______ ________ ___.
_______ _____ _____ _______ ________ ____ ______ ____.
_____ ________ ________ ______ __________ ________ _______ __________ _________ _________.
_____ ____ ___ _________ ______ ___ _______ _____.
___ _________ ________ ______ _____.
________ _________.
IGNOU ACADEMY
Your IGNOU journey, made easier.
- Solved Assignments
- Study Notes
- Guess Papers
- Question Papers
Continue Reading — It's Free
Sign in with Google to unlock more of this answer.
✓ Free access
✓ Unlock up to 60% of the answer
✓ No payment required
✓ Unlock up to 60% of the answer
✓ No payment required
Quick Google sign-in. No separate registration form.