Search results for: XGBoost

Authors: Ehsan Mehryaar, Reza Bushehri

Abstract:

One of the principal parameters defining the clay soil dynamic response is the strain-shear modulus relation. Predicting the strain and, subsequently, shear modulus reduction of the soil is essential for performance analysis of structures exposed to earthquake and dynamic loadings. Many soil properties affect soil’s dynamic behavior. In order to capture those effects, in this study, a database containing 1193 data points consists of maximum shear modulus, strain, moisture content, initial void ratio, plastic limit, liquid limit, initial confining pressure resulting from dynamic laboratory testing of 21 clays is collected for predicting the shear modulus vs. strain curve of soil. A model based on an extreme gradient boosting technique is proposed. A tree-structured parzan estimator hyper-parameter tuning algorithm is utilized simultaneously to find the best hyper-parameters for the model. The performance of the model is compared to the existing empirical equations using the coefficient of correlation and root mean square error.

Keywords: XGBoost, hyper-parameter tuning, soil shear modulus, dynamic response

Procedia PDF Downloads 200

Authors: Saurabh Kumar

Abstract:

In the fiercely competitive landscape of e-commerce, understanding and mitigating customer churn has become paramount for sustainable business growth. This paper presents a thorough investigation into the application of machine learning techniques for churn prediction in e-commerce, aiming to provide actionable insights for businesses seeking to enhance customer retention strategies. We conduct a comparative study of various machine learning algorithms, including traditional statistical methods and ensemble techniques, leveraging a rich dataset sourced from Kaggle. Through rigorous evaluation, we assess the predictive performance, interpretability, and scalability of each method, elucidating their respective strengths and limitations in capturing the intricate dynamics of customer churn. We identified the XGBoost classifier to be the best performing. Our findings not only offer practical guidelines for selecting suitable modeling approaches but also contribute to the broader understanding of customer behavior in the e-commerce domain. Ultimately, this research equips businesses with the knowledge and tools necessary to proactively identify and address churn, thereby fostering long-term customer relationships and sustaining competitive advantage.

Keywords: customer churn, e-commerce, machine learning techniques, predictive performance, sustainable business growth

Procedia PDF Downloads 26

Authors: Akshay Paranjape, Nils Plettenberg, Robert Schmitt

Abstract:

Traditional optimization methods like evolutionary algorithms are widely used in production processes to find an optimal or near-optimal solution of control parameters based on the simulated environment space of a process. These algorithms are computationally intensive and therefore do not provide the opportunity for real-time optimization. This paper utilizes the Deep Reinforcement Learning (DRL) framework to find an optimal or near-optimal solution for control parameters. A model based on maximum a posteriori policy optimization (Hybrid-MPO) that can handle both numerical and categorical parameters is used as a benchmark for comparison. A comparative study shows that DRL can find optimal solutions of similar quality as compared to evolutionary algorithms while requiring significantly less time making them preferable for real-time optimization. The results are confirmed in a large-scale validation study on datasets from production and other fields. A trained XGBoost model is used as a surrogate for process simulation. Finally, multiple ways to improve the model are discussed.

Keywords: reinforcement learning, evolutionary algorithms, production process optimization, real-time optimization, hybrid-MPO

Procedia PDF Downloads 110

Authors: Aref Aasi, Sahar Ebrahimi Bajgani, Erfan Aasi

Abstract:

Breast cancer (BC) continues to be the most frequent cancer in females and causes the highest number of cancer-related deaths in women worldwide. Inspired by recent advances in studying the relationship between different patient attributes and features and the disease, in this paper, we have tried to investigate the different classification methods for better diagnosis of BC in the early stages. In this regard, datasets from the University Hospital Centre of Coimbra were chosen, and different machine learning (ML)-based and neural network (NN) classifiers have been studied. For this purpose, we have selected favorable features among the nine provided attributes from the clinical dataset by using a random forest algorithm. This dataset consists of both healthy controls and BC patients, and it was noted that glucose, BMI, resistin, and age have the most importance, respectively. Moreover, we have analyzed these features with various ML-based classifier methods, including Decision Tree (DT), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machine (SVM) along with NN-based Multi-Layer Perceptron (MLP) classifier. The results revealed that among different techniques, the SVM and MLP classifiers have the most accuracy, with amounts of 96% and 92%, respectively. These results divulged that the adopted procedure could be used effectively for the classification of cancer cells, and also it encourages further experimental investigations with more collected data for other types of cancers.

Keywords: breast cancer, diagnosis, machine learning, biomarker classification, neural network

Procedia PDF Downloads 134

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

Neural network approaches are machine learning methods used in many domains, such as healthcare and cyber security. Neural networks are mostly known for dealing with image datasets. While training with the images, several fundamental mathematical operations are carried out in the Neural Network. The operation includes a number of algebraic and mathematical functions, including derivative, convolution, and matrix inversion and transposition. Such operations require higher processing power than is typically needed for computer usage. Central Processing Unit (CPU) is not appropriate for a large image size of the dataset as it is built with serial processing. While Graphics Processing Unit (GPU) has parallel processing capabilities and, therefore, has higher speed. This paper uses advanced Neural Network techniques such as VGG16, Resnet50, Densenet, Inceptionv3, Xception, Mobilenet, XGBOOST-VGG16, and our proposed models to compare CPU and GPU resources. A system for classifying autism disease using face images of an autistic and non-autistic child was used to compare performance during testing. We used evaluation matrices such as Accuracy, F1 score, Precision, Recall, and Execution time. It has been observed that GPU runs faster than the CPU in all tests performed. Moreover, the performance of the Neural Network models in terms of accuracy increases on GPU compared to CPU.

Keywords: autism disease, neural network, CPU, GPU, transfer learning

Procedia PDF Downloads 117

Authors: Simone Leonardi, Luca Ardito

Abstract:

Micro-influencers are effective elements in the marketing strategies of companies and institutions because of their capability to create an hyper-engaged audience around a specific topic of interest. In recent years, many scientific approaches and commercial tools have handled the task of detecting this type of social media users. These strategies adopt solutions ranging from rule based machine learning models to deep neural networks and graph analysis on text, images, and account information. This work compares the existing solutions and proposes an ensemble method to generalize them with different input data and social media platforms. The deployed solution combines deep learning models on unstructured data with statistical machine learning models on structured data. We retrieve both social media accounts information and multimedia posts on Twitter and Instagram. These data are mapped into feature vectors for an eXtreme Gradient Boosting (XGBoost) classifier. Sixty different topics have been analyzed to build a rule based gold standard dataset and to compare the performances of our approach against baseline classifiers. We prove the effectiveness of our work by comparing the accuracy, precision, recall, and f1 score of our model with different configurations and architectures. We obtained an accuracy of 0.91 with our best performing model.

Keywords: deep learning, gradient boosting, image processing, micro-influencers, NLP, social media

Procedia PDF Downloads 183

Authors: Sudhir Kumar Singh, Debashish Chakravarty

Abstract:

Slope stability analysis is an important aspect in the field of geotechnical engineering. It is also important from safety, and economic point of view as any slope failure leads to loss of valuable lives and damage to property worth millions. This paper aims at mitigating the risk of slope failure by studying the effect of different joint sets on the stability of mine pit slopes under the influence of various external factors, namely degree of saturation, rainfall intensity, and seismic coefficients. Supervised machine learning approach has been utilized for making accurate and reliable predictions regarding the stability of slopes based on the value of Factor of Safety. Numerous cases have been studied for analyzing the stability of slopes using the popular Finite Element Method, and the data thus obtained has been used as training data for the supervised machine learning models. The input data has been trained on different supervised machine learning models, namely Random Forest, Decision Tree, Support vector Machine, and XGBoost. Distinct test data that is not present in training data has been used for measuring the performance and accuracy of different models. Although all models have performed well on the test dataset but Random Forest stands out from others due to its high accuracy of greater than 95%, thus helping us by providing a valuable tool at our disposition which is neither computationally expensive nor time consuming and in good accordance with the numerical analysis result.

Keywords: finite element method, geotechnical engineering, machine learning, slope stability

Procedia PDF Downloads 99

Authors: Junyu Chen, Peng Xu

Abstract:

In the context of global efforts to enhance building energy efficiency, accurate thermal load forecasting is crucial for both device sizing and predictive control. Variable Refrigerant Flow (VRF) systems are widely used in buildings around the world, yet VRF zonal load prediction has received limited attention. Due to differences between VRF zones in building-level prediction methods, zone-level load forecasting could significantly enhance accuracy. Given that modern VRF systems generate high-quality data, this paper introduces transfer learning to leverage this data and further improve prediction performance. This framework also addresses the challenge of predicting load for building zones with no historical data, offering greater accuracy and usability compared to pure white-box models. The study first establishes an initial variable set of VRF zonal building loads and generates a foundational white-box database using EnergyPlus. Key variables for VRF zonal loads are identified using methods including SRRC, PRCC, and Random Forest. XGBoost and LSTM are employed to generate pre-trained black-box models based on the white-box database. Finally, real-world data is incorporated into the pre-trained model using transfer learning to enhance its performance in operational buildings. In this paper, zone-level load prediction was integrated with transfer learning, and a framework was proposed to improve the accuracy and applicability of VRF zonal load prediction.

Keywords: zonal load prediction, variable refrigerant flow (VRF) system, transfer learning, energyplus

Procedia PDF Downloads 28

Authors: Jacky Liu

Abstract:

This paper develops a team sports outcome prediction system with potential for wide-ranging applications across various disciplines. Despite significant advancements in predictive analytics, existing studies in sports outcome predictions possess considerable limitations, including insufficient feature engineering and underutilization of advanced machine learning techniques, among others. To address these issues, we extend the Sports Cross Industry Standard Process for Data Mining (SRP-CRISP-DM) framework and propose a unique, comprehensive predictive system, using National Basketball Association (NBA) data as an example to test this extended framework. Our approach follows a holistic methodology in feature engineering, employing both Time Series and Non-Time Series Data, as well as conducting Explanatory Data Analysis and Feature Selection. Furthermore, we contribute to the discourse on target variable choice in team sports outcome prediction, asserting that point spread prediction yields higher profits as opposed to game-winner predictions. Using machine learning algorithms, particularly XGBoost, results in a significant improvement in predictive accuracy of team sports outcomes. Applied to point spread betting strategies, it offers an astounding annual return of approximately 900% on an initial investment of $100. Our findings not only contribute to academic literature, but have critical practical implications for sports betting. Our study advances the understanding of team sports outcome prediction a burgeoning are in complex system predictions and pave the way for potential profitability and more informed decision making in sports betting markets.

Keywords: machine learning, team sports, game outcome prediction, sports betting, profits simulation

Procedia PDF Downloads 102

Authors: Wade Ghribi, Abdelmoty M. Ahmed, Ahmed Said Badawy, Belgacem Bouallegue

Abstract:

In higher education institutions, the most pressing priority is to improve student performance and retention. Large volumes of student data are used in Educational Data Mining techniques to find new hidden information from students' learning behavior, particularly to uncover the early symptom of at-risk pupils. On the other hand, data with noise, outliers, and irrelevant information may provide incorrect conclusions. By identifying features of students' data that have the potential to improve performance prediction results, comparing and identifying the most appropriate ensemble learning technique after preprocessing the data, and optimizing the hyperparameters, this paper aims to develop a reliable students' performance prediction model for Higher Education Institutions. Data was gathered from two different systems: a student information system and an e-learning system for undergraduate students in the College of Computer Science of a Saudi Arabian State University. The cases of 4413 students were used in this article. The process includes data collection, data integration, data preprocessing (such as cleaning, normalization, and transformation), feature selection, pattern extraction, and, finally, model optimization and assessment. Random Forest, Bagging, Stacking, Majority Vote, and two types of Boosting techniques, AdaBoost and XGBoost, are ensemble learning approaches, whereas Decision Tree, Support Vector Machine, and Artificial Neural Network are supervised learning techniques. Hyperparameters for ensemble learning systems will be fine-tuned to provide enhanced performance and optimal output. The findings imply that combining features of students' behavior from e-learning and students' information systems using Majority Vote produced better outcomes than the other ensemble techniques.

Keywords: educational data mining, student performance prediction, e-learning, classification, ensemble learning, higher education

Procedia PDF Downloads 106

Authors: Mahmoud Huleihel, George Abu-Aqil, Manal Suleiman, Klaris Riesenberg, Itshak Lapidot, Ahmad Salman

Abstract:

Urinary tract infections (UTIs) are considered to be the most common bacterial infections worldwide, which are caused mainly by Escherichia (E.) coli (about 80%). Klebsiella pneumoniae (about 10%) and Pseudomonas aeruginosa (about 6%). Although antibiotics are considered as the most effective treatment for bacterial infectious diseases, unfortunately, most of the bacteria already have developed resistance to the majority of the commonly available antibiotics. Therefore, it is crucial to identify the infecting bacteria and to determine its susceptibility to antibiotics for prescribing effective treatment. Classical methods are time consuming, require ~48 hours for determining bacterial susceptibility. Thus, it is highly urgent to develop a new method that can significantly reduce the time required for determining both infecting bacterium at the species level and diagnose its susceptibility to antibiotics. Fourier-Transform Infrared (FTIR) spectroscopy is well known as a sensitive and rapid method, which can detect minor molecular changes in bacterial genome associated with the development of resistance to antibiotics. The main goal of this study is to examine the potential of FTIR spectroscopy, in tandem with machine learning algorithms, to identify the infected bacteria at the species level and to determine E. coli susceptibility to different antibiotics directly from patients' urine in about 30minutes. For this goal, 1600 different E. coli isolates were isolated for different patients' urine sample, measured by FTIR, and analyzed using different machine learning algorithm like Random Forest, XGBoost, and CNN. We achieved 98% success in isolate level identification and 89% accuracy in susceptibility determination.

Keywords: urinary tract infections (UTIs), E. coli, Klebsiella pneumonia, Pseudomonas aeruginosa, bacterial, susceptibility to antibiotics, infrared microscopy, machine learning

Procedia PDF Downloads 170

Authors: Vishal Das, Tianyi Mao, Zhicheng Geng, Carmen Flores, Diego Pelloso, Fang Wang

Abstract:

Accurate sell-in and sell-out forecasting is a ubiquitous problem in the retail industry. It is an important element of any demand planning activity. As a global food and beverage company, Nestlé has hundreds of products in each geographical location that they operate in. Each product has its sell-in and sell-out time series data, which are forecasted on a weekly and monthly scale for demand and financial planning. To address this challenge, Nestlé Chilein collaboration with Amazon Machine Learning Solutions Labhas developed their in-house solution of using machine learning models for forecasting. Similar products are combined together such that there is one model for each product category. In this way, the models learn from a larger set of data, and there are fewer models to maintain. The solution is scalable to all product categories and is developed to be flexible enough to include any new product or eliminate any existing product in a product category based on requirements. We show how we can use the machine learning development environment on Amazon Web Services (AWS) to explore a set of forecasting models and create business intelligence dashboards that can be used with the existing demand planning tools in Nestlé. We explored recent deep learning networks (DNN), which show promising results for a variety of time series forecasting problems. Specifically, we used a DeepAR autoregressive model that can group similar time series together and provide robust predictions. To further enhance the accuracy of the predictions and include domain-specific knowledge, we designed an ensemble approach using DeepAR and XGBoost regression model. As part of the ensemble approach, we interlinked the sell-out and sell-in information to ensure that a future sell-out influences the current sell-in predictions. Our approach outperforms the benchmark statistical models by more than 50%. The machine learning (ML) pipeline implemented in the cloud is currently being extended for other product categories and is getting adopted by other geomarkets.

Keywords: sell-in and sell-out forecasting, demand planning, DeepAR, retail, ensemble machine learning, time-series

Procedia PDF Downloads 272

Authors: Amadou Wurry Jallow, Adama N. S. Bah, Karamo Bah, Shih-Ye Wang, Kuo-Chung Chu, Chien-Yeh Hsu

Abstract:

Chronic kidney disease (CKD) is a major public health challenge with high prevalence, rising incidence, and serious adverse consequences. Developing effective risk prediction models is a cost-effective approach to predicting and preventing complications of chronic kidney disease (CKD). This study aimed to develop an accurate machine learning model that can dynamically identify individuals at risk of CKD using various kinds of diagnostic data, with or without laboratory data, at different follow-up points. Creatinine is a key component used to predict CKD. These models will enable affordable and effective screening for CKD even with incomplete patient data, such as the absence of creatinine testing. This retrospective cohort study included data on 19,429 adults provided by a private research institute and screening laboratory in Taiwan, gathered between 2001 and 2015. Univariate Cox proportional hazard regression analyses were performed to determine the variables with high prognostic values for predicting CKD. We then identified interacting variables and grouped them according to diagnostic data categories. Our models used three types of data gathered at three points in time: non-laboratory, laboratory, and metabolic indices data. Next, we used subgroups of variables within each category to train two machine learning models (Random Forest and XGBoost). Our machine learning models can dynamically discriminate individuals at risk for developing CKD. All the models performed well using all three kinds of data, with or without laboratory data. Using only non-laboratory-based data (such as age, sex, body mass index (BMI), and waist circumference), both models predict chronic kidney disease as accurately as models using laboratory and metabolic indices data. Our machine learning models have demonstrated the use of different categories of diagnostic data for CKD prediction, with or without laboratory data. The machine learning models are simple to use and flexible because they work even with incomplete data and can be applied in any clinical setting, including settings where laboratory data is difficult to obtain.

Keywords: chronic kidney disease, glomerular filtration rate, creatinine, novel metabolic indices, machine learning, risk prediction

Procedia PDF Downloads 105

Authors: Elżbieta Turska

Abstract:

Introduction: One of the most difficult times in a person’s life is adolescence. The experiences in this period may shape the future life of this person to a large extent. This is the reason why many young people experience sadness, dejection, hopelessness, sense of worthlessness, as well as losing interest in various activities and social relationships, all of which are often classified as mood disorders. As many as 15-40% adolescents experience depressed moods and for most of them they resolve and are not carried into adulthood. However, (5-6%) of those affected by mood disorders develop the depressive syndrome and as many as (1-3%) develop full-blown clinical depression. Materials: A large questionnaire was given to 2508 students, aged 13–16 years old, and one of its parts was the Burns checklist, i.e. the standard test for identifying depressed mood. The questionnaire asked about many aspects of the student’s life, it included a total of 53 questions, most of which had subquestions. It is important to note that the data suffered from many problems, the most important of which were missing data and collinearity. Aim: In order to identify the correlates of mood disorders we built predictive models which were then trained and validated. Our aim was not to be able to predict which students suffer from mood disorders but rather to explore the factors influencing mood disorders. Methods: The problems with data described above practically excluded using all classical statistical methods. For this reason, we attempted to use the following Artificial Intelligence (AI) methods: classification trees with surrogate variables, random forests and xgboost. All analyses were carried out with the use of the mlr package for the R programming language. Resuts: The predictive model built by classification trees algorithm outperformed the other algorithms by a large margin. As a result, we were able to rank the variables (questions and subquestions from the questionnaire) from the most to least influential as far as protection against mood disorder is concerned. Thirteen out of twenty most important variables reflect the relationships with parents. This seems to be a really significant result both from the cognitive point of view and also from the practical point of view, i.e. as far as interventions to correct mood disorders are concerned.

Keywords: mood disorders, adolescents, family, artificial intelligence

Procedia PDF Downloads 100

Authors: Xingyu Gao, Qiang Wu

Abstract:

Patents play a crucial role in protecting innovation and intellectual property. Early prediction of the impact of artificial intelligence (AI) patents helps researchers and companies allocate resources and make better decisions. Understanding the key factors that influence patent impact can assist researchers in gaining a better understanding of the evolution of AI technology and innovation trends. Therefore, identifying highly impactful patents early and providing support for them holds immeasurable value in accelerating technological progress, reducing research and development costs, and mitigating market positioning risks. Despite the extensive research on AI patents, accurately predicting their early impact remains a challenge. Traditional methods often consider only single factors or simple combinations, failing to comprehensively and accurately reflect the actual impact of patents. This paper utilized the artificial intelligence patent database from the United States Patent and Trademark Office and the Len.org patent retrieval platform to obtain specific information on 35,708 AI patents. Using six machine learning models, namely Multiple Linear Regression, Random Forest Regression, XGBoost Regression, LightGBM Regression, Support Vector Machine Regression, and K-Nearest Neighbors Regression, and using early indicators of patents as features, the paper comprehensively predicted the impact of patents from three aspects: technical, social, and economic. These aspects include the technical leadership of patents, the number of citations they receive, and their shared value. The SHAP (Shapley Additive exPlanations) metric was used to explain the predictions of the best model, quantifying the contribution of each feature to the model's predictions. The experimental results on the AI patent dataset indicate that, for all three target variables, LightGBM regression shows the best predictive performance. Specifically, patent novelty has the greatest impact on predicting the technical impact of patents and has a positive effect. Additionally, the number of owners, the number of backward citations, and the number of independent claims are all crucial and have a positive influence on predicting technical impact. In predicting the social impact of patents, the number of applicants is considered the most critical input variable, but it has a negative impact on social impact. At the same time, the number of independent claims, the number of owners, and the number of backward citations are also important predictive factors, and they have a positive effect on social impact. For predicting the economic impact of patents, the number of independent claims is considered the most important factor and has a positive impact on economic impact. The number of owners, the number of sibling countries or regions, and the size of the extended patent family also have a positive influence on economic impact. The study primarily relies on data from the United States Patent and Trademark Office for artificial intelligence patents. Future research could consider more comprehensive data sources, including artificial intelligence patent data, from a global perspective. While the study takes into account various factors, there may still be other important features not considered. In the future, factors such as patent implementation and market applications may be considered as they could have an impact on the influence of patents.

Keywords: patent influence, interpretable machine learning, predictive models, SHAP

Procedia PDF Downloads 48