An Empirical Analysis of Three-Stage Data-Preprocessing for Analogy-Based Software Effort Estimation on the ISBSG Data

Huang, Jianglin; Li, Yan‐Fu; Keung, Jacky; Yu, Yuen Tak; Chan, W. K.

doi:10.1109/qrs.2017.54

Cited by 13 publications

(17 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data pre-processing techniques include reduction, projection, and missing data techniques (MDTs). Data reduction decreases the data size via, for example, feature selection (FS) or dimension reduction [12].…”

Section: Data Preprocessingmentioning

confidence: 99%

Forecasting Gold Price in Rupiah using Multivariate Analysis with LSTM and GRU Neural Networks

Primananda¹,

Isa²

2021

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Forecasting the gold price movement's volatility has essential applications in areas such as risk management, options pricing, and asset allocation. The multivariate model is expected to generate more accurate forecasts than univariate models in time series data like gold prices. Multivariate analysis is based on observation and analysis of more than one statistical variable at a time. This paper mainly builds a multivariate prediction model based on Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) model to analyze and forecast the price of the gold commodity. In addition, the prediction model is optimized with a Cross-Validated Grid Search to find the optimum hyperparameter. The empirical results show that the proposed Timeseries Prediction model has an excellent accuracy in prediction, that proven by the lowest Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). Overall, in more than three years data period, LSTM has high accuracy, but for under three years period, GRU does better. This research aims to find a promising methodology for gold price forecasting with high accuracy.

show abstract

Section: Data Preprocessingmentioning

confidence: 99%

Forecasting Gold Price in Rupiah using Multivariate Analysis with LSTM and GRU Neural Networks

Primananda¹,

Isa²

2021

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…kNNI is a well-known and computationally simple method for missing data imputation that uses observations in the environment to account for missing values [15][16][17][18]. In addition, kNN can predict categorical or numeric attributes using the value of mode/mean or median [19].…”

Section: Introductionmentioning

confidence: 99%

“…For empirical validation, the ML algorithm is routinely tested on the SEE datasets. The use of data preprocessing (DP) techniques as a fundamental step in helping to increase machine learning performance [15,16,21].…”

Section: Introductionmentioning

confidence: 99%

Empirical Analysis of Software Effort Preprocessing Techniques Based on Machine Learning

2021

IJIES

View full text Add to dashboard Cite

“…A number of studies have tried to modify new models using machine learning to improve accuracy in software effort estimation [3] [15] [16] [17]. Using a based feature selection [18] [19] [20] [21], or parameter optimization [22] [23][24]. Some prediction techniques have been suggested but none have proved consistently successful in predicting software development efforts [11].…”

Section: Introductionmentioning

confidence: 99%

Optimizing Software Effort Estimation Models Based On Metaheuristic Methods: A Proposed Framework

Marco¹

2019

IJATCSE

View full text Add to dashboard Cite

Software effort estimation are part of the field of project management in software that is very important for development efforts. Software development planning is something very complex and serious, which determines the success of a software project. Because of the lack of good requirements and information, it causes software project failures. Although there are many studies that aim to solve the problem of noisy, irrelevant and excessive data to achieve accuracy. The purpose of this study is to combine metaheuristic optimization techniques as a framework for using Machine Learning models. By proposing a hybrid estimation model based on a combination of the Satin Bowerbird Optimizer (SBO) algorithm and Support Vector Regression (SVR) to improve the accuracy of software estimation efforts. This study is to determine the effort estimation and duration estimation. The proposed framework is based on theoretical concepts. the proposed model will be tested using a heterogeneous dataset, namely the ISBSG dataset. the results of the study are expected to be used as decision making as the initial planning of software project development.

show abstract

An Empirical Analysis of Three-Stage Data-Preprocessing for Analogy-Based Software Effort Estimation on the ISBSG Data

Cited by 13 publications

References 44 publications

Forecasting Gold Price in Rupiah using Multivariate Analysis with LSTM and GRU Neural Networks

Forecasting Gold Price in Rupiah using Multivariate Analysis with LSTM and GRU Neural Networks

Empirical Analysis of Software Effort Preprocessing Techniques Based on Machine Learning

Optimizing Software Effort Estimation Models Based On Metaheuristic Methods: A Proposed Framework

Contact Info

Product

Resources

About