No abstract

Abstract-Predictive analytic modeling is the key step involved in building a successful Data Mining solution. Predictive analytic modeling is a set of iterative activities in which a predictive model is built from the observed data set. Predictive analytics is the area of data mining concerned with the prediction of future probabilities and trends using archive data. It brings together management, information technology and modeling that eases researchers in making suitable predictions. Many methodologies have been proposed for model building, and these are based on some basic industrial engineering frameworks. The proposed research work discusses CRISP, DMAIC and SEMMA methodologies which provide the building blocks for an efficient predictive model. Keywords-Predictive Analytics, Data Mining, Modeling, CRISP, DMAIC and SEMMA. I. INTRODUCTIONToday's demanding atmosphere is forcing more organizations to explore and adopt predictive analytics. Data being the indispensible assets of an organization is increasing exponentially and so does the data storage need. Selling large amount of data has little value, but if one can add insight via analytics to data then we have the opportunity to monetize it. There is a sea change in the corporate world, researchers and IT organizations can seize upon the opportunity to reinvent themselves and transform from a support function into a profit center [1]. "We are sitting on a mountain of gold but we're not mining it as effectively as we could," says Michael Masciandaro, director of business intelligence at Rohm & Haas, a global specialty materials manufacturer. Data Mining is the technique that retrieves useful information from large amounts of data. Data mining is defined as a process involving the extraction of useful and interesting information from the underlying data [2]. Modeling is the main part of Predictive Analytics. Predictive Analytics modeling is used in representation of real world situations for rendering or description of reality. Limited, imprecise, but useful, a model helps us to make sense of the world [3]. The result of the models may give important information that can be used in decision making and future prediction. Predictive Analytic Modeling helps in optimizing existing processes, better understanding and predicting customer behavior, identify unexpected opportunities and recessions, and predict problems before they happen. The core of predictive analytics relies on capturing relationships between explanatory variables and the predicted variables from past occurrences, and exploiting them to predict the unknown outcome. It is important to note, however, that the accuracy and usability of results will depend greatly on the level of data analysis and the quality of assumptions [4]. Predictive analytic modeling involves searching for meaningful relationships among variables and representing those relationships in models. These variables are called predictors and constitute the core element of predictive analytics. A predictor could be measured for an indi...

This paper develops a rainfall prediction technique, named GWO-based Linear Regression (GWLR) model, using the linear regression model and Grey Wolf Optimizer (GWO). The linear regression model is used to predict the value of a dependent variable from an independent variable on the basis of regression coefficient. The proposed GWLR predicts rainfall based on the input time-series weather data using the proposed GWLR model, in which the regression coefficients are obtained optimally using the GWO. Thus, the rainfall detection is done on the accumulated data of India and the state, Jammu and Kashmir over the years 1901 to 2015. The effectiveness of the proposed GWLR is checked with MSE and PRD values and is evaluated to be the best when compared to other existing techniques with least MSE value as 0.005 and PRD value as 1.700%.

The high growth in education is increasing the demand for flexible and innovative approaches to Teaching -learning in which information technology can play a crucial role. In an educational system "teaching" and "learning" are the two major activities besides "assessment" which is a coordinating activity. The Information Communication Technology (ICT) has a potential to transform the different areas of the educational system. In this paper our focus is on identifying the challenges prevailing in our educational system and proposing the role of Information Communication Technology practices in its successful implementation. This paper also provides some recommendations which could be used as a catalyst for promotion of information communication technology services in both teaching and learning.

Prediction of rainfall is one of the most essential and demanding tasks for the weather forecasters since ages. Rainfall prediction plays an important role in the field of farming and industries. Precise rainfall prediction is vital for detecting the heavy rainfall and to provide the information of warnings regarding the natural calamities. Rainfall prediction involves recording the various parameters of weather like wind direction, wind speed, humidity, rainfall, temperature etc. From last few decades, it has been seen that data mining techniques have achieved good performance and accuracy in weather prediction than traditional statistical methods. This research work aims to compare the performance of few data mining algorithms for predicting rainfall using historical weather data of Srinagar, India, which is collected from http://www.wundergrounds.com website. From the collected weather data which comprises of 9 attributes, only 5 attributes which are most relevant to rainfall prediction are considered. Data mining process model is followed to obtain accurate and correct prediction results. In this paper, various data mining algorithms were explored which include decision tree based J48, Random forest, Naive Bayes, Bayes Net, Logistic Regression, IBk, PART and bagging. The experimental results show that J48 algorithm has good level of accuracy than other algorithms.