Essay On Data Mining

739 Words2 Pages

Data mining techniques discovers the novel, valid, frequent pattern from the large data set. The problems of data mining range from association rule mining, classification to feature extraction and others. Now in the era of internet, the data generated can be measured in terabytes or petabytes. This large amount of data contain huge amount of hidden information that can be useful to many businesses. On this account, there is requirement of efficient and cost-effective approaches and techniques of data mining that can handle this large scale data. The cloud computing provide the environments that are suitable for the tasks of large data mining. The cloud data mining has applications in various domains of biology, banking, pharmacy, chemoinformatics, marketing and many more. The cloud computing is the practice that enables access to the shared pool of configurable computing resources which can be dynamically provisioned. It refers to both the applications delivered as service as well as hardware and system software in the data centres that provide those services. The attractive features of cloud computing such as on-demand access, high scalability, reliability, cost savings, low maintenance and energy efficiency bring benefits to both cloud service consumers and providers. 2. RELATED WORK The different cost models for data mining techniques are as following The cost model for distributed data mining in [1] gives the apriori estimates of the response time for the given task considering a specific architectural model. The distributed data mining response time T is given as T = tddm + tki Where tddm is time taken to do mining in distributed environment and tki is time taken to do knowledge integration. The factors that determine tdd... ... middle of paper ... ...that indicates the scale of the current market. The pricing model for frequent users that have long term requirement can be given as PriceSaaSB = PriceSaaS – Rtot *(k1 * time + k2 *no)/Roc Where PriceSaaS is price for short term users, Rtot is total amount of resources, time duration for which user will occupy certain resources, k1 and k2 are time factor and amount factor respectively. The authors introduced the cost model for cloud storaage[] that consider the system’s design access cost, usage cost, variable cost , discount cost and compensation cost. Therefore the total cost of a user in agiven period of time is given as Cij = Cija + Ciju + Cijf - Cijp -Cijb Where Cij is total cost, Cija is access cost, Ciju is usage cost, Cijf is variable cost , Cijp is discount cost and Cijb is compensation cost and i and j are the user level and service model respectively

Open Document