No abstract

No abstract

No abstract

Objectives: To design and develop an enhanced ensemble model for residential energy consumption prediction using time series analysis. Methods:The system is consistent of an ensemble made from two time series models, which are later combined to produce a final prediction through the use of bagging techniques. The energy profile is built for this study using the data collected from a single-phase Minion Energy Monitor, installed in residential buildings, which is developed by Minion Labs India Private Limited. Samples are collected for a time of 7 days with a two second interval. This data is then restructured and normalized for it to fit the enhanced ensemble model of Long Short-Term Memory (LSTM) and Vector Autoregression (VAR) using bagging techniques and weighted average to obtain the predictions.Findings: The proposed model has produced an enhanced R2 score of 98.99% when compared to LSTM (74.85%), SVM (62.41%), VAR (82.914%) and ARIMA (93.152%) standalone models. It makes use of an analyzed lag variable to reduce computation complexity and resource utilization. Further, an ensemble technique is used to pick out the strengths of two models. An analysis performed showed that this architecture is 6.08% better than the algorithms for LSTM and VAR individually. Novelty: A data driven solution is proposed in this study through the enhancement of existing models to create an ensemble and thereby creating a stable structure that predicts values using a weighted average. The weighted average ensures that precise outputs are obtained by giving more importance to predictions that are closer to the actual values. The use of a lag variable further increases the efficiency, learning rate, dealing with non-linear features, less error and faster training of the proposed architecture. All these factors also aid in improving the accuracy for a time series data prediction.

Objectives: Credit fraud is a global threat to financial institutions due to specific challenges like imbalanced datasets and hidden patterns in real-life scenarios. The objective of this study is to propose a model that effectively identifies fraudulent transactions. Methods: Methods such as Synthetic Minority Oversampling Technique (SMOTE) and Generative Adversarial Networks (GAN) that artificially generate synthetic data are used in this paper to approximate the distribution of data among the two classes in the original dataset. After balancing the dataset, the individual models Multi-Layer Perceptron (MLP), k-Nearest Neighbors algorithm (kNN) and Support Vector Machine (SVM) are trained on the augmented dataset to establish an initial improvement at the data level. These base-classifiers are further incorporated into the Optimized Stacked Ensemble (OSE) learning process to fit the meta-classifier which creates an effective predictive model for fraud detection. All base-classifiers and the final Optimized Stacked Ensemble (OSE) have been implemented to critically assess and evaluate their performances. Findings: Empirical results obtained in this paper show that the quality of the final dataset is considerably improved when Synthetic Minority Oversampling Technique (SMOTE) and Generative Adversarial Networks (GAN) are used as oversampling algorithms. The Multi-Layer Perceptron model showed an increase of 10% in the F1 Score while kNN and SVM showed an increase of 3% each. The optimized model is built using a Stacking Classifier that combines the GAN-improved Multi-Perceptron Model with the other standard classification models such as KNN and SVM. This ensemble outperforms the existing enhanced Multi-Layer Perceptron with near-perfect accuracy (99.86%) and an increase of 16% in F1 Score, resulting in an effective fraud detection mechanism. Novelty: For the current dataset, the Optimized Stacked Ensemble model shows an increase of 16% in F1 Score as compared to the existing Multi-Perceptron model.

No abstract

No abstract

No abstract