Ensemble of Supervised and Unsupervised Learning Models to Predict a Profitable Business Decision

Heidari, Maryam; Zad, Samira; Rafatirad, Setareh

doi:10.1109/iemtronics52119.2021.9422649

Cited by 31 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We applied the Momentum Stochastic Gradient Descent (SGD) algorithm to train models with a batch size of 20, a learning rate of 10 −3 , a decay rate of 2.86 × 10 −5 , and a momentum of 0.9 for the 35 epochs. The system was implemented using Keras 3 . We applied PCC to measure the correlation between the predicted values and the evaluation scores from the dataset as ground truths for 100 floor plans in the test data.…”

Section: Methodsmentioning

confidence: 99%

“…The number of train/validation/test data were set to 3040/380/380, respectively, and we trained the segmentation prediction network model to learn the correspondence between the floor plan images and the ground truth (GT) label masks using the training and validation data. After the training, 3 https://keras.io the test data was used for evaluation with a metric mean intersection over union (IoU) [88] defined by (1), where n c is the number of classes, t i is the total number of pixels belonging to class i, and n j is the total number of predicted as class j belonging to class i.…”

Section: A Baseline Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Subjective Functionality and Comfort Prediction for Apartment Floor Plans and Its Application to Intuitive Online Property Search

Narahara

Yamasaki

2023

IEEE Trans. Multimedia

View full text Add to dashboard Cite

This paper presents a new user experience for online apartment search using functionality and comfort as query items. Specifically, it has three technical contributions. First, we present a new dataset on the perceived functionality and comfort scores of residential floor plans using nine question statements about the level of comfort, openness, privacy, etc. Second, we propose an algorithm to predict the scores from the floor plan images. Lastly, we implement a new apartment search system and conduct a large-scale usability study using crowdsourcing. The experimental results show that our apartment search system can provide a better user experience. To the best of our knowledge, this is the first work to propose a highly accurate machine learning model for predicting the subjective functionality and comfort of apartments.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: A Baseline Methodsmentioning

confidence: 99%

Subjective Functionality and Comfort Prediction for Apartment Floor Plans and Its Application to Intuitive Online Property Search

Narahara

Yamasaki

2023

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…When predictive performance accuracy is the main goal then decision tree models should be taken into consideration. In many fields, including real estate price prediction, machine learning algorithms are now widely available as techniques that can be utilized to carry out prediction and classification tasks 7 …”

Section: Literature Reviewmentioning

confidence: 99%

“…In many fields, including real estate price prediction, machine learning algorithms are now widely available as techniques that can be utilized to carry out prediction and classification tasks. 7 Multiple linear regression techniques have also been implemented in house price prediction problems. They assess the relationship that exists between the dependent variable and independent variables.…”

Section: Predictive Modelsmentioning

confidence: 99%

A boosting ensemble learning based hybrid light gradient boosting machine and extreme gradient boosting model for predicting house prices

Sibindi¹,

Mwangi

Waititu

2022

Engineering Reports

View full text Add to dashboard Cite

The implementation of tree‐ensemble models has become increasingly essential in solving classification and prediction problems. Boosting ensemble techniques have been widely used as individual machine learning algorithms in predicting house prices. One of the techniques is LGBM algorithm that employs leaf wise growth strategy, reduces loss and improves accuracy during training which results in overfitting. However, XGBoost algorithm uses level wise growth strategy which takes time to compute resulting in higher computation time. Nevertheless, XGBoost has a regularization parameter, implements column sampling and weight reduction on new trees which combats overfitting. This study focuses on developing a hybrid LGBM and XGBoost model in order to prevent overfitting through minimizing variance whilst improving accuracy. Bayesian hyperparameter optimization technique is implemented on the base learners in order to find the best combination of hyperparameters. This resulted in reduced variance (overfitting) in the hybrid model since the regularization parameter values were optimized. The hybrid model is compared to LGBM, XGBoost, Adaboost and GBM algorithms to evaluate its performance in giving accurate house price predictions using MSE, MAE and MAPE evaluation metrics. The hybrid LGBM and XGBoost model outperformed the other models with MSE, MAE and MAPE of 0.193, 0.285, and 0.156 respectively.

show abstract

“…Menerapkan algoritma machine learning untuk melakukan prediksi sewa rumah bukanlah tren yang baru. Pada Ensemble of Supervised and Unsupervised Learning Models to Predict a Profitable Business Decision menggunakan metode Random Forest dan Multilayer Perceptron [5]. House Price Forecasting using Data Mining menggunakan algoritma multiple linear regression [6].…”

Section: Pendahuluanunclassified

Perbandingan Gradient Boosting dan Light Gradient Boosting Dalam Melakukan Klasifikasi Rumah Sewa

Dahlia

Agustyaningrum

2022

JNKTI

View full text Add to dashboard Cite

Abstrak— Persaingan antar perusahaan tidak akan dapat terhindarkan apalagi terkait tujuan perusahaan dalam mendapatkan omset sebesar-besarnya. Salah satu persaingan yang terjadi adalah dibidang property atau jika lebih spesifik lagi yaitu penyewaan rumah. Sebuah perusahaan harus menentukan strategi bagaimana rumah yang akan disewakan nantinya akan sebanding dengan harga pembangunan. Maka dari itu perusahaan dapat melakukan klasifikasi rumah sewa dalam menentukan hal tersebut. Penelitian ini menggunakan model Gradient Boosting dan Light Gradient Boosting. Hasil yang didapatkan adalah bahwa model Gradient Boosting adalah model yang cocok pada penelitian ini dengan mendapatkan hasil accuracy 84.38%, precision 83.33% dan recall 87.53%. Jika dilihat perbandingan dari confusion matrix, Gradient Boosting memiliki jumlah hasil prediksi data lebih besar dibanding dibanding Light Gradient Boosting.Kata kunci: Rumah Sewa, Data Mining, Gradient Boosting, Light Gradient Boosting Abstract— Competition between companies cannot be avoided, especially regarding the company's goal of getting the maximum turnover. One of the competitions that occurs is in the property sector, or more specifically, house rental. A company must determine a strategy for how the house to be rented out will be comparable to the construction price. Therefore the company can classify rental houses in determining this. This study uses the Gradient Boosting and Light Gradient Boosting models. The results obtained are that the Gradient Boosting model is a suitable model in this study with 84.38% accuracy, 83.33% precision and 87.53% recall. If you look at the comparison of the confusion matrix, Gradient Boosting has a greater number of data prediction results than Light Gradient Boosting.Keywords : House for rent, Data Mining, Gradient Boosting, Light Gradient Boosting

show abstract

Ensemble of Supervised and Unsupervised Learning Models to Predict a Profitable Business Decision

Cited by 31 publications

References 24 publications

Subjective Functionality and Comfort Prediction for Apartment Floor Plans and Its Application to Intuitive Online Property Search

Subjective Functionality and Comfort Prediction for Apartment Floor Plans and Its Application to Intuitive Online Property Search

A boosting ensemble learning based hybrid light gradient boosting machine and extreme gradient boosting model for predicting house prices

Perbandingan Gradient Boosting dan Light Gradient Boosting Dalam Melakukan Klasifikasi Rumah Sewa

Contact Info

Product

Resources

About