Support vector regression‐based imputation in analogy‐based software development effort estimation

Abstract

Missing data (MD) is a widespread problem that can affect the ability to use data to construct effective software development effort estimation (SDEE) techniques. To deal with this challenge, several imputation techniques have been investigated in SDEE and k‐nearest neighbors (KNN)‐based imputation is still the most frequently used. To the best of our knowledge, no study has used support vector regression (SVR)‐based imputation to construct accurate estimation techniques, in particular those based on analogy. This paper introduces a new imputation technique based on SVR for handling MD in two analogy‐based SDEE techniques: classical analogy and fuzzy analogy. More specifically, we investigate whether the use of SVR instead of KNN in imputing MD improves the predictive performance of these two analogy‐based techniques. A total of 1134 experiments were conducted involving seven datasets, SVR/KNN MD imputation techniques (KNN with Euclidean and Manhattan distances), three missingness mechanisms (missing completely at random, missing at random, non‐ignorable missing), and MD percentages from 10% to 90%. The results suggest that the use of SVR imputation, rather than KNN imputation, may improve the prediction performance of both analogy‐based techniques. Furthermore, we found that the impact of MD percentage upon effort prediction performance is reduced when using SVR rather than KNN. Moreover, fuzzy analogy generates better estimates in terms of the standardized accuracy measure than classical analogy regardless of the MD technique, the dataset used, the missingness mechanism, or the MD percentage.

Fuzzy case‐based‐reasoning‐based imputation for incomplete data in software engineering repositories

“…• Parameter of fuzziness m controls the extent of sharing among fuzzy clusters. 24,48 In other words, low values of m mean that the project is more likely to belong to one cluster while high values mean that the project is more likely to belong to more clusters. Based on our previous study, 24 we range the parameter m from 1.5 to 3.5 with increments of 0.5.…”

“…49 The most commonly used approach to decide the optimal cluster number is executing the clustering algorithm several times with a different number of clusters and then selecting the cluster number that provides the best result according to a predefined criterion. 48 The predefined criterion function is called the cluster validity index.…”

“…Although the validity indexes are primarily used to decide upon the optimal number of clustering k, it can also be used to determine the optimal parameter of fuzziness m as well. 48 This study used the validity index of 49 in order to determine m, k, and β. Consequently, a grid search was performed, and the Tsekouras index was calculated for each configuration (m, k, and β). The optimal configuration is determined when the Tsekouras index reaches its lowest value.…”

Comparing Statistical and Machine Learning Imputation Techniques in Breast Cancer Classification

“…In this framework, the observed data are considered as a training set for the learning model, which is then applied to the data with missing values to impute. K-Nearest Neighbor (KNN) [ 17 ], Decision Tree (DT) [ 18 ] and Support Vector Regression (SVR) [ 19 ] are the most used ML techniques for imputation and achieved great success [ 20 ].…”

Analysis of cluster center initialization of 2FA‐kprototypes analogy‐based software effort estimation

“…Therefore, feature subset selection techniques should be applied to find the optimal set of features . Another important limitation of ASEE techniques is their inability to handle missing values …”