Online ISSN: 2515-8260

Keywords : regression model


Assessing the Relative Importance of Predictors in Linear Regression

Srinivasa Rao. D; S Jyothi Kannipamula

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 970-976

Regression is the most extensively used statistical technique for explaining theoretical relationships and for prediction. This method can be viewed as a mapping from input or response variables space to an outcome variable space. If the assumption of the model is met, metrics like R2 F statistic and significance of t-values of the regression coefficients are used to judge the goodness of fit of the regression model. Similarly Mean Square Error (MSE) is used to judge the predictive power of the regression model. For judging the relative importance of the response variables in an estimated regression model, the magnitude and signs of the regression coefficients are considered. However, this approach is quite arbitrary and many a times inconclusive. In this context the present paper demonstrates the use of some of the relative importance metrics (lmg (Lindemann, Merenda and Gold,1980, pmvd (Feldman,2005)) which provides the decomposition of variance explained by a regression model into nonnegative components. It is shown that these relative measures are comparatively better than the magnitude and sign of regression parameters for assessing the relative importance of individual predictors in regression.

Web based Tender Bid Analysis and Recommendation System using Collaborative Filtering

Jaichandran R; Muthuselvan S; Usha Kiruthika; Raja prakash S; Veda Priyan; Mathi B

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 3031-3038

Now a days all government projects, infrastructure enhancement are provided to individuals through tender system. But in the exiting approach, there is no transparency and government officials intervention is there, because of this the right vendor might be missed to get the order as there is lack of transparency. To address this issue, a web based tender analysis and recommendation system is proposed system using collaborative filtering. Proposed method selects the best bid provided by the vendors for a respective tender. It also provides transparency and enhances opportunity for new vendors to participate in bid. For experimental results, we used java for this web based tender analysis and recommendation system. Promising results obtained by continuously refining the trained model utilizing new goals information, scope of type of tenders and anticipating whether any activity is specified. The proposed system saves time of processing, easy decision making, reduces tender costs for governments and motivates new players to participate and perform the bid.