International Journals
Permanent URI for this collectionhttps://dspace.psgrkcw.com/handle/123456789/115
Browse
4 results
Search Results
Item FOIL BASED FEATURE SUBSET SELECTION ALGORITHM FOR PREDICTING INFERTILITY ON IVF USING CLUSTERING(Speak Foundation-International Journal of Management and Social Sciences(IJMSS), 2018-12) S, Deepika; M, RajeswariThis paper illustrates the concept of clustering and classification technique to identify important criteria for the infertility couples to find the success rate of In-vitro Fertilization treatment. A FOIL algorithm, First creates the construction of minimum spanning tree after that the partition the data into each tree by clustering the similar features. Selected features are represented into clusters. At last feature interaction is done by combining the features appeared in the previous circumstances of all FOIL rules, which will achieve a candidate feature subset to avoid redundant features and reserves interactive ones. Thus, the proposed paper will determine the accuracy and efficiency of IVF treatment using R programming.Item PREDICT CUSTOMER CHURN THROUGH CLASS IMBALANCE WITH MODIFIED RIPPER ALGORTHIM(Speak Foundation-International Journal of Management and Social Sciences(IJMSS), 2018-12) M, Rajeswari; S, DeepikaCompetitive advantage is gained by firm through new areas such as data warehousing, data mining and campaign management software have made Customer Relationship Management(CRM). This research aims to develop methodologies for predicting customer churn in advance, while keeping misclassification rates to a minimum.Item INFERTILITY PREDICTIVE ANALYSIS ON IVF BASAED ON SIGNIFICANT FEATURE SELECTION USING DATA MINING TECHNIQUES(Speak Foundation-International Journal of Management and Social Sciences(IJMSS), 2018-12) S, Deepika; M, RajeswariThis paper elucidates the process by applying clustering and classification technique to spot major procedures for the infertility couples to decide the success rate of In-vitro Fertilization treatment. There are factors which lead to infertility like age, education, economical backlog, Body Mass Index(BMI) and obesity which causes changes in hormonal levels and heredity etc., for infertility couples. The constraints with high sway factor can be well-known by apply the proper decrease/unrelated algorithm, which destroy the parameters that has a less important role in determining the success rate of particular patients. Data mining plays vital role in its pre-processing techniques to increase prediction accuracy and find which treatment will be perfect for the patient. A FAST-FOIL algorithm, First became the construction of minimum spanning tree, after that the partition the data into each tree by clustering the similar features. Selected features are represented into clusters. Thus, the proposed paper will determine the accuracy of IVF treatment compared with ZIFT and GIFT using MATLAB.Item DEVELOPMENT OF MODIFIED RIPPER ALGORITHM TO PREDICT CUSTOMER CHURN(International Journal of Advance Research in Engineering Science and Technology, 2018-02) M, RajeswariTechnologies such as data warehousing, data mining, and campaign management software have made Customer Relationship Management (CRM) a new area where firms can gain a competitive advantage. Particularly through data mining a process of extracting hidden predictive information from large databases, organizations can identify their valuable customers, predict future behaviors, and enable firms to make proactive, knowledge-driven decisions. Data Mining along with Customer Relationship Management plays a vital role in today’s business environment. Customer churn, a process of retaining customer is a major issue. Prevention of customer churn is a major problem because acquiring new customer is more expensive than holding existing customers. In order to prevent churn several data mining techniques have been proposed. One among such method is solving class imbalance which has not received much attention in the context of data mining. This paper describes Customer Relationship Management (CRM), customer churn and class imbalance and proposes a methodology for preventing customer churn through class imbalance.