Can automatic personal categorization deal with user inconsistency

This paper will discuss the intricacies of data and its abilities to automate user information from domain hierarchies. The paper will discuss the advent of data based on normalization standards and derive an understanding to rectify anomalies from automation standpoint. It will also discuss the standards of clustering and finding data definitions where numbers can quantify data. The paper will also discuss the SOM and LVQ, which both adhered to data mapping.
Automatic Personal Categorization can deal with user inconsistency in many ways. First and foremost, automation obtains information derived from user text fields, which is then converted into data that can be used. Automation has redundancy checks that are embedded to ensure that anomalies are detected. Discrepancies in data seems to be problematic because it hinders automation in manipulation of data and created dynamic inventory queries to facilitate the business. The challenge in many organizations is the fact that majority of decisions are made based on estimated guesses. This paper will discuss many ways in which data has been skewed because of user inconsistency and discuss fault tolerance to reduce these errors. This paper will discuss the results of the experiment in user modeling and to measure sampling.
Another way to mitigate this risk is to establish parameters of normalization. This is a huge aspect in databases where data s gathered from databases. Normalization for instance takes duplicate or same records and combines it to one field. Goren(2001) Normalization in any automated environment is guided through mapping similar data items to the same cell on the grid. Data mapping is a generic brand of creating large clusters of data pool in which SOM and LVQ are used frequently.
The most current form of automation is seen in SQL databases and parsing of data that is generated in user forms. For instance, Attribute maximization is to validate a page for data maximization. When the user inputs data in a webpage, it requires authentication and validation. Additionally, validating a webpage requires a comprehensive encryption and security protocols. XML is essential for parsing and passing data. XML allows storage tags in which data is encapsulated and sent. XML validator that produces easy to read error messages and asks for missing files through data tags. Validating documents can go through data parsing or encryption via SSL
Parsing is a popular form of user form data validation that takes facilitation of data mapping in which algorithms work together. Calculations, word processing, and excels also came later as basic processing and storage were the primitive examples of LVQ and SOM. The test was conducted to understand user automation based on two prescribed methods. These two methods compromised of the learning vector quantization (LVQ) algorithm is a supervised competitive ANN and SOM(self-organizing map) which were both utilized for the study.
Goren(2001) The results confirmed In order to evaluate the system performance in light of user data inconsistency, the following experiment was performed. Moreover, the users in a given sample size asked to reclassify the messages from original classification. The main purpose of this work was to test the possibility of automating the classification of subjectively categorized data sets from the data derived. The results confirmed that there is a possible to automate data with a subjective categorization. Both LVQ and SOM surpassed user categorization based on the hypothesis for automation process. This confirms that both can be used for data mapping purposes in software and databases as defining parameters for thresholds and to seek user discrepancies. For larger understanding of this, a future recommendation would be to study a larger of raw data to gather a better analysis.
References
Goren-Bar, D., & Kuflik, T. Can Automatic Personal Categorization deal with User
Inconsistency?. Recommendation and Personalization in eCommerce, 116.
Foulds, L. R., and M. West. Identifying factors for large-scale business information system
application development productivity improvement . Hamilton, N. Z.: Dept. of
Management Systems, Waikato Management School, University of Waikato, 2006