Scientific Data Research Articles

Python code for modeling ARIMA-LSTM architecture with random forest algorithm

Over conventional statistical models, machine learning mechanisms are establishing themselves as a potential area for modeling and forecasting complex time series. Because it can integrate several forecasting methodologies’ capabilities, hybrid time series models are fundamental in data science. Here, we present a Python script that builds a combined architecture of the ARIMA-LSTM model with random forest technique to generate a high-accuracy prediction. This script is a step-by-step process to create a statistical and then machine learning model through statistical assumption.

Discrimination of Brazilian green canephora coffees beans by ultraviolet–visible spectroscopy as non-target analysis: A tool for recognizing geographical indications

Specialty green coffee beans have a higher commercial value and some of them have recently been classified in Brazil based on the indication of provenance and denomination of origin. In this context, the classification of the type of coffee bean is still a challenge, using traditional analytical techniques. Thus, alternative analytical techniques, such as ultraviolet–visible spectroscopy (UV–Vis), as non-target analysis can be applied as a quick and reliable method of coffee classification using data science, such as chemometric tools. In the present study, UV–Vis were evaluated as a new strategy for discrimination of green beans of Brazilian specialty canephora coffees with recognized geographical indications (Robusta Amazônico and Conilon from state of Espírito Santo), for the first time. Spectra obtained from the aqueous extract of 221 samples. The Principal Component Analysis (PCA) was performed and subsequently Partial Least Squares with Discriminant Analysis (PLS-DA) model developed. The PCA indicated tendency to group the samples in their respective classes, pointing to the similarities in the spectra of samples of the same origin. The PLS-DA model obtained showed figures of merit values starting at 89.3% in the test set. The VIP scores showed that the variables associated with chlorogenic acids, caffeine and chlorophyll are the most important for differentiating the studied coffees. The results obtained showed that UV–Vis fingerprint − non-targeted analysis associated with PLS-DA is appropriate for the discrimination of green beans of Brazilian specialty coffee from different origins, in a simple way, using common equipment in several laboratories.

Modeling Risk Assessment of Soil Heavy Metal Pollution using Partial Least Squares and Fuzzy Logic: A Case Study of a Gully Type Coal-Based Solid Waste Dumpsite

Continuous release and migration of heavy metals from coal-based solid waste (CSW) dumpsites often results in significant encroachment on ecological lands and pollution of natural environments. As a result, there is an urgent need for long-term and rapid monitoring, analysis, and assessment to control environmental risks associated with large CSW dumpsites. We constructed a new composite model (PLS-FL) that uses partial least squares regression (PLSR) and fuzzy logic inference (FLI) to accurately predict heavy metal concentrations in soils and assess pollution risk levels. The potential application of the PLS-FL was tested through a gully type CSW case study. We compared 20 modeling strategies using the PLS-FL: five types heavy metals (Cd, Zn, Pb, Cr and As) * four spectral transformation methods (first derivative (FD), second derivative (SD), reverse logarithm (RL), and continuum removal (CR)) * one variable selection method (competitive adaptive reweighted sampling (CARS)). The results showed that the combination of derivative transformation and CARS was recommended for estimation, with R2 C > 0.80 and R2 P > 0.50. When comparing the PLSR model with four traditional machine learning methods (Support Vector Machines (SVM), Random Forests (RF), Extreme Learning Machines (ELM), and KNN), the PLSR model demonstrated the highest average prediction accuracy. Additionally, the FLI process no longer relies on human perception and expert opinion, enhancing the model's objectivity and reliability. The evaluation results revealed that the heavy metal contamination areas of the CSW dumpsite are concentrated at the bottom of the gully, with more severe contamination in the north. Furthermore, a high-risk zone exists in the interim storage area for CSW to the east of the dump. These findings align with the initial detections at the sampling sites and highlight the need for targeted monitoring and control in these areas. The application of the model will empower regulators to quickly assess the overall situation of large-scale heavy metal pollution and provide scientific program and data support for continuous large-scale pollution risk monitoring and sustainable risk management.

Biological Potential and Therapeutic Effectiveness of Hinokiflavone in Medicine: The Effective Components of Herbal Medicines for Treatment of Cancers and Associated Complications

Background: Plants have been providing us medicines and food material for centuries. Traditional system of medicine, including Ayurveda, and Traditional Chinese medicines have been playing important role in health sectors for the treatment of human disorders since very early age. Plant secondary metabolites, including flavonoids, coumarins, saponins, and tannins have significant therapeutic potential in medicine. Biflavonoids are dimers of flavonoids, linked by a C–O–C or C–C bond. Hinokiflavone is an important class of biflavonoids found to be present in Toxicodendron succedaneum, Isophysis tasmanica, Juniperus rigida, Juniperus phoenicea, Platycladi cacumen, Rhus succedanea, Selaginella tamariscina, Platycladus orientalis, Selaginella bryopteris, and Metasequoia glyptostroboides. Methods: Biological potential of hinokiflavone in medicine have been analyzed in the present work through scientific data analysis of various literature work. Scientific database, including Google, Scopus, Science Direct, and PubMed were searched to collect all the scientific information of the present work using terms flavonoid, biflavonoid, herbal medicine, and hinokiflavone. Pharmacological activities of hinokiflavone were analyzed in the present work in very detailed manner. Analytical data of hinokiflavone were collected and analyzed in present work in order to know the biological source of hinokiflavone. Results: Present work signified the biological importance of hinokiflavone against various types of cancerous disorders, including breast cancer, colorectal cancer, esophageal squamous cancer, adenocarcinoma, hepatocellular carcinoma, myeloid leukemia, and melanoma. Further, its antiinflammatory, hepatoprotective, anti-viral, and anti-oxidant potential were also discussed in the present work. Moreover, its biological potential against COVID-19 and hair loss, and procoagulant activity were also summarized in this paper. Analytical data on hinokiflavone signified the importance of various analytical techniques in the extraction, separation, and identification of hinokiflavone with their pharmacokinetic parameters. Conclusion: Present work signified the biological importance and therapeutic potential of hinokiflavone in medicine.

A workflow management system for reproducible and interoperable high-throughput self-driving experiments

To foster self-driving experimentation and address the reproducibility crisis in bioprocess development in a collaborative environment, a modular Workflow Management System (WMS) is required. In this work, a WMS based on Directed Acyclic Graphs that offers a modular and flexible design for plug-and-play integration of computational tools is presented. A case study is used to demonstrate that the implementation of a computational WMS in robotic experimental facilities promotes the application of Findable, Accessible, Interoperable and Re-usable principles, allowing researchers to readily share protocols, models, methods and data. As a proof of concept, we integrated three different computational workflows for online re-design of feeding rates in 24 parallel E. coli fed-batch cultivations producing elastin-like proteins. This approach provides a solid foundation for increasing scientific data generation in robotic experimental facilities, fostering open collaboration, and addressing the challenges of reproducibility in research.

PROV-IO: A Cross-Platform Provenance Framework for Scientific Data on HPC Systems

PROV-IO: A Cross-Platform Provenance Framework for Scientific Data on HPC Systems

The bumpy road to conservation: challenges and opportunities in updating the Galapagos zoning system

In 2014, the Galapagos National Park Directorate, sponsored by various international non-governmental organizations, initiated a comprehensive marine and terrestrial spatial planning process to improve the management effectiveness of Galapagos’ protected areas. This effort aimed to reconfigure management areas by expanding or redistributing no-take zones to protect Key Biodiversity Areas and ensure the conservation of at least 30% of terrestrial and marine ecosystems in the Galapagos. However, this process encountered significant challenges, notably the erosion of fishers' trust following the implementation of a "Marine Sanctuary". This top-down decision resulted in socio-political tension, compelling the Ecuadorian government to delay the implementation of the new marine zoning until there was conclusive scientific data on its socio-economic impact on local small-scale fishers’ livelihoods. This paper examines the achievements and shortcomings of the Galapagos zoning update process, highlighting the successful integration of scientific zoning criteria and the enhanced protection of critical biodiversity areas, together with the reduced support from fishers and legal disputes. To move forward, we recommended a bottom-up approach centered on rebuilding trust among the fishing community via innovative engagement strategies and the introduction of market incentives to promote sustainable practices. Assessing the long-term impact of no-take zones is essential for refining management approaches. Additionally, the application of cutting-edge technology within an adaptive co-management model is recommended to improve fisheries and ecological data gathering and analysis, facilitating proactive and well-informed management decisions. Our suggestions aim to reconcile conservation objectives with the needs and aspirations of the local communities in this iconic archipelago.

Developing an Educational Chatbot for Scientific Data Management Course Using DialogFlow

Developing an Educational Chatbot for Scientific Data Management Course Using DialogFlow

Ambush strategy enhances organisms’ performance in rock–paper–scissors games

We study a five-species cyclic system wherein individuals of one species strategically adapt their movements to enhance their performance in the spatial rock–paper–scissors game. Environmental cues enable the awareness of the presence of organisms targeted for elimination in the cyclic game. If the local density of target organisms is sufficiently high, individuals move towards concentrated areas for direct attack; otherwise, they employ an ambush tactic, maximising the chances of success by targeting regions likely to be dominated by opponents. Running stochastic simulations, we discover that the ambush strategy enhances the likelihood of individual success compared to direct attacks alone, leading to uneven spatial patterns characterised by spiral waves. We compute the autocorrelation function and measure how the ambush tactic unbalances the organisms’ spatial organisation by calculating the characteristic length scale of typical spatial domains of each species. We demonstrate that the threshold for local species density influences the ambush strategy’s effectiveness, while the neighbourhood perception range significantly impacts decision-making accuracy. The outcomes show that long-range perception improves performance by over 60%, although there is potential interference in decision-making under high attack triggers. Understanding how organisms’ adaptation their environment enhances their performance may be helpful not only for ecologists, but also for data scientists, aiming to improve artificial intelligence systems.

Web mining and sentiment analysis of COVID-19 discourse in online forum communities

Recently, various discussions, solutions, data, and methods related to coronavirus disease 2019 (COVID-19) have been posted in online forum communities. Although a vast amount of posting on COVID-19 analytical projects are available in the online forum communities, much of them remain untapped due to limited overview and profiling that focuses on COVID-19 analytic techniques. Thus, it is quite challenging for information diggers and researchers to distinguish the recent trends and challenges of COVID-19 analytic for initiating different and critical studies to fight against the coronavirus. This paper presents the findings of a study that executed a web mining process on COVID-19 data analytical projects from the Stack Overflow and GitHub online community platforms for data scientists. This study provides an insight on what activities can be conducted by novice researchers and others who are interested in data analysis, especially in sentiment analysis. The classification results via Naïve Bayes (NB), support vector machine (SVM) and logistic regression (LR) have returned high accuracy, indicating that the constructed model is efficient in classifying the sentiment data of COVID-19. The findings reported in this paper not only enhance the understanding of COVID-19 related content and analysis but also provides promising framework that can be applied in diverse contexts and domains.

Artificial intelligence and design of experiments for resource adequacy assessment in power systems

Assessing the effects of the energy transition and liberalization of energy markets on resource adequacy is an increasingly important and demanding task. The rising complexity of energy systems requires adequate methods for energy system modeling leading to increased computational requirements. Furthermore, with complexity, uncertainty increases likewise calling for probabilistic assessments and scenario analyses. To adequately and efficiently address these various requirements, new methods from the field of data science are needed to accelerate current modeling approaches. With our systematic literature review, we want to close the gap between the three disciplines (1) resource adequacy assessments, (2) artificial intelligence (AI), and (3) design of experiments. For this, we conduct a large-scale systematic review of selected fields of application and methods and make a synthesis that relates the different disciplines to each other. Among other findings, we identify metamodeling of complex probabilistic resource adequacy assessment models using AI methods and applications of AI-based methods for forecasts of storage dispatch and (non-)availabilities as promising fields of application that have not yet been sufficiently covered. Eventually, we define a new methodological pipeline for adequately and efficiently addressing the present and upcoming challenges in the assessment of resource adequacy accounting for modeling the complexity and uncertainties of future developments.

ASF-YOLO: A novel YOLO model with attentional scale sequence fusion for cell instance segmentation

We propose a novel Attentional Scale Sequence Fusion based You Only Look Once (YOLO) framework (ASF-YOLO) which combines spatial and scale features for accurate and fast cell instance segmentation. Built on the YOLO segmentation framework, we employ the Scale Sequence Feature Fusion (SSFF) module to enhance the multiscale information extraction capability of the network, and the Triple Feature Encoder (TFE) module to fuse feature maps of different scales to increase detailed information. We further introduce a Channel and Position Attention Mechanism (CPAM) to integrate both the SSFF and TFE modules, which focus on informative channels and spatial position-related small objects for improved detection and segmentation performance. Experimental validations on two cell datasets show remarkable segmentation accuracy and speed of the proposed ASF-YOLO model. It achieves a box mAP of 0.91, mask mAP of 0.887, and an inference speed of 47.3 FPS on the 2018 Data Science Bowl dataset, outperforming the state-of-the-art methods. The source code is available at https://github.com/mkang315/ASF-YOLO.

From hearing to seeing: Linking auditory and visual place perceptions with soundscape-to-image generative artificial intelligence

People experience the world through multiple senses simultaneously, contributing to our sense of place. Prior quantitative geography studies have mostly emphasized human visual perceptions, neglecting human auditory perceptions at place due to the challenges in characterizing the acoustic environment vividly. Also, few studies have synthesized the two-dimensional (auditory and visual) perceptions in understanding human sense of place. To bridge these gaps, we propose a Soundscape-to-Image Diffusion model, a generative Artificial Intelligence (AI) model supported by Large Language Models (LLMs), aiming to visualize soundscapes through the generation of street view images. By creating audio-image pairs, acoustic environments are first represented as high-dimensional semantic audio vectors. Our proposed Soundscape-to-Image Diffusion model, which contains a Low-Resolution Diffusion Model and a Super-Resolution Diffusion Model, can then translate those semantic audio vectors into visual representations of place effectively. We evaluated our proposed model by using both machine-based and human-centered approaches. We proved that the generated street view images align with our common perceptions, and accurately create several key street elements of the original soundscapes. It also demonstrates that soundscapes provide sufficient visual information places. This study stands at the forefront of the intersection between generative AI and human geography, demonstrating how human multi-sensory experiences can be linked. We aim to enrich geospatial data science and AI studies with human experiences. It has the potential to inform multiple domains such as human geography, environmental psychology, and urban design and planning, as well as advancing our knowledge of human-environment relationships.

Photonic data analysis in 2050

Photonic data analysis is a field at the intersection of imaging, spectroscopy, machine learning, and computer science. The diversity of both data types and application scenarios requires flexibility in the methods applied, combining a full range of computational methods, from classical chemometric techniques to state-of-the-art deep learning solutions. Interdisciplinary and international collaborations are needed to accelerate the progress of photonic data science. An underlying data infrastructure and standardization will be needed to provide collaborative platforms for research on data comparability, enabling the integration of novel photonic techniques into routine applications. The increasing complexity of the questions being investigated requires the application of more sophisticated data-driven models, which may only be optimized for large data sets. Unfortunately, novel techniques in the early stages of development can rarely provide a variability of measured samples sufficient to build a generalizable complex model. To overcome this problem, state-of-the-art methods will emerge for working with extremely limited or unbalanced data, as well as for dealing with device-to-device variation. Further developments are also foreseen in computable artificial intelligence methods, which will allow the validation of models of any architecture by comparing them with the knowledge of the researchers.

Automated Machine Learning and Explainable AI (AutoML-XAI) for Metabolomics: Improving Cancer Diagnostics.

Metabolomics generates complex data necessitating advanced computational methods for generating biological insight. While machine learning (ML) is promising, the challenges of selecting the best algorithms and tuning hyperparameters, particularly for nonexperts, remain. Automated machine learning (AutoML) can streamline this process; however, the issue of interpretability could persist. This research introduces a unified pipeline that combines AutoML with explainable AI (XAI) techniques to optimize metabolomics analysis. We tested our approach on two data sets: renal cell carcinoma (RCC) urine metabolomics and ovarian cancer (OC) serum metabolomics. AutoML, using Auto-sklearn, surpassed standalone ML algorithms like SVM and k-Nearest Neighbors in differentiating between RCC and healthy controls, as well as OC patients and those with other gynecological cancers. The effectiveness of Auto-sklearn is highlighted by its AUC scores of 0.97 for RCC and 0.85 for OC, obtained from the unseen test sets. Importantly, on most of the metrics considered, Auto-sklearn demonstrated a better classification performance, leveraging a mix of algorithms and ensemble techniques. Shapley Additive Explanations (SHAP) provided a global ranking of feature importance, identifying dibutylamine and ganglioside GM(d34:1) as the top discriminative metabolites for RCC and OC, respectively. Waterfall plots offered local explanations by illustrating the influence of each metabolite on individual predictions. Dependence plots spotlighted metabolite interactions, such as the connection between hippuric acid and one of its derivatives in RCC, and between GM3(d34:1) and GM3(18:1_16:0) in OC, hinting at potential mechanistic relationships. Through decision plots, a detailed error analysis was conducted, contrasting feature importance for correctly versus incorrectly classified samples. In essence, our pipeline emphasizes the importance of harmonizing AutoML and XAI, facilitating both simplified ML application and improved interpretability in metabolomics data science.

Positive relationship between bird diversity and human mental health: an analysis of repeated cross-sectional data

An increasing body of research has examined the link between biodiversity of birds and human mental health, but most studies only use cross-sectional data. Few studies have used longitudinal or repeated cross-sectional data to investigate the mental health benefits of bird diversity. The aim of this study is to analyse the relationship between bird diversity and mental health at the national level using a unique repeated cross-sectional dataset. I used repeated cross-sectional health data from the German National Cohort health study, collected between March, 2014, and September, 2019, and annual bird citizen science data to investigate the effects of bird-diversity exposure on mental health. Mental health was measured using the summary score of the Patient Health Questionnaire depression module 9 (SumPHQ) and the Short Form Health Survey-12 Mental Health Component Scale. As a proxy for bird diversity, I created a unique indicator called reporting-rate richness and combined it with the health data. Reporting-rate richness measures the number of bird species within postcode areas across Germany in probabilities while accounting for variation in survey efforts. Alternative indicators of bird diversity, such as bird-species richness or abundance, were also calculated. Associations between bird diversity and mental health were estimated using linear regression with region and time fixed effects, adjusted for a range of sociodemographic and environmental confounders and spatial autocorrelation. Interaction terms between income levels and reporting-rate richness were also analysed to examine the moderating effect of socioeconomic status. I did the analyses for an unbalanced (n=176 362) and balanced (n=125 423) dataset, with the balanced dataset comprising only regions (postcode areas) in which health data were available for each year. The linear fixed-effects regression analysis indicated a significant negative association between reporting-rate richness and SumPHQ, as observed in both the unbalanced dataset (β -0·02, p=0·017) and the balanced dataset (β -0·03, p=0·0037). Similarly, regression results with both datasets showed a positive relationship between reporting-rate richness and Mental Health Component Scale (MCS; unbalanced β 0·02, p=0·0086; balanced β 0·03, p=0·0018). The moderator analyses revealed a significant influence of socioeconomic status on the relationship between reporting-rate richness and mental health. The robustness of these findings was confirmed through sensitivity analyses. The results suggest that a greater likelihood of having many different bird species in a person's area of residence might positively contribute to mental health, especially for people with lower socioeconomic status. These findings could have implications for biodiversity conservation and health policy decisions, as governments are facing challenges such as global biodiversity loss and growing public mental health problems. None.

Advancing data honesty in experimental biology.

The ease with which scientific data, particularly certain types of raw data in experimental biology, can be fabricated without trace begs urgent attention. This is thought to be a widespread problem across the academic world, where published results are the major currency, incentivizing publication of (usually positive) results at the cost of lax scientific rigor and even fraudulent data. Although solutions to improve data sharing and methodological transparency are increasingly being implemented, the inability to detect dishonesty within raw data remains an inherent flaw in the way in which we judge research. We therefore propose that one solution would be the development of a non-modifiable raw data format that could be published alongside scientific results; a format that would enable data authentication from the earliest stages of experimental data collection. A further extension of this tool could allow changes to the initial original version to be tracked, so every reviewer and reader could follow the logical footsteps of the author and detect unintentional errors or intentional manipulations of the data. Were such a tool to be developed, we would not advocate its use as a prerequisite for journal submission; rather, we envisage that authors would be given the option to provide such authentication. Only authors who did not manipulate or fabricate their data can provide the original data without risking discovery, so the mere choice to do so already increases their credibility (much like 'honest signaling' in animals). We strongly believe that such a tool would enhance data honesty and encourage more reliable science.

Big Data Analysis for Product Demand Prediction in Indonesian E-commerce

The Indonesian e-commerce sector has witnessed exponential growth in recent years, necessitating effective strategies for predicting product demand to meet consumer expectations and stay competitive. Leveraging big data analytics offers a promising solution to this challenge, allowing businesses to harness vast volumes of data to forecast demand accurately. This research explores the utilization of big data analysis for product demand prediction in Indonesian e-commerce through a qualitative analysis approach. Interviews with e-commerce executives, data scientists, and industry experts revealed key themes, including data quality and integration, analytical techniques and tools, and organizational culture and capability. Results highlight the challenges, opportunities, and best practices associated with leveraging big data analytics for demand prediction in Indonesian e-commerce, providing valuable insights for businesses striving to optimize their predictive capabilities and enhance decision-making processes in this dynamic and rapidly evolving market.

Supporting the COVID Response with Solutions from Science

January 2023 marks the 36th month following the World Health Organization’s declaration of COVID-19 as a public health emergency of international concern. Recent and upcoming events show how far the Philippines has come in terms of its response: emerging from what has been referred to as the world’s longest lockdown1, crowds converging in public spacesand participating in mass gatherings demonstrate how people are adapting to COVID-19 as a reality of daily life. The journey to this milestone has not been simple nor straightforward. In addition to the thousands of health care workers who provide frontline services, a multi-disciplinary group of scientists continues to work tirelessly in the background, dedicating their efforts to gain a better understanding of COVID, particularly in the Philippine context. For example:1. The Philippines has contributed over 12,000 sequences to the Global Initiative on Sharing Avian Influenza Data (GISAID) platform.2 This resource provides open access to genomic data on coronavirus and allows real-time surveillance to monitor the emergence of new COVID-19 variants globally.2. The FASSSTER (Feasibility Analysis of Syndromic Surveillance Using Spatio-Temporal Epidemiological Modeler) team of computer and data scientists, mathematical and economics modelers, public health and epidemiological experts provides scenario-based projections for COVID-19 using a disease surveillance and modeling platform.3The platform outputs guide decision making by national and local government agencies for interventions such as community quarantines, granular lockdowns, and vaccination targets.3. The Department of Science and Technology is supporting more than 60 projects and studies through its ARCHER (Addressing and Responding to COVID-19 Through Health Research) program. Aside from the usual focus on diagnosis, treatment and prevention, work is also being done on a broad range of topics, such as AI/ICT-driven prediction models and COVID behavior studies.4 Even as scientists struggled to provide information and technology solutions to guide a rational response, governments followed their advice to varying degrees, sometimes resulting in confusing messages. The pandemic has truly highlighted the “synergies as well as the tensions between science and policy.”5Yin and colleagues explored the connection between science and policy in their 2021 paper published in Science. Matching the scientific references in policy documents obtained from a large-scale database with another publication and citation database provided the team with a “distinct opportunity to examine the role of science in the global policy responseto COVID-19.” They found that policy documents in the COVID-19 pandemic substantially access recent, peer-reviewed, and highimpact science. However, national policy approaches have varied greatly, with some countries being actively antagonistic to scientific advice.6 In a perfect world, science and government should work closely together to formulate evidence-based policy. Bicchieri et al. found the largest gaps between trust in science and trust in government in Colombia and Mexico; in contrast, the smallest were in Germany and South Korea, where policy and science were more aligned. They note that “country-level trust in science, and not in government, becomes a strong predictor of compliance.”7 According to the United Nations Department of Economic and Social Affairs, the pandemic response requires a more collaborative relationship between scientists and policymakers. Their recommendations include strengthened use of science in policy, ensuring “open science,” universal access to solutions, and a faster response to scientific findings. Of note, the need for building public trust in science is also emphasized.8 For science to be able to provide solutions to support the COVID response, it must communicate, and it must be heard.

Big Data Analytics: Analyzing the Significance of it in Light to Indian Banking Sector

Abstract: Banks are the engines that drive the financial sector, monetary markets, and economic expansion. Since the introduction of information technology (IT) in the 1980s, 1990s, and 2000s, the Indian banking sector has experienced a number of changes in terms of how IT is applied to various banking operations from different perspectives, such as cutting expenses, earning revenue, detection of fraud, security concerns, etc. These changes are still ongoing with the emergence of new trends like business intelligence and big data analytics. Banks are utilizing big data to their advantage. To obtain a general competitive edge, they push for innovations in data and analytics through the use of big data and data science. Due to the vast amount of data about transactions that banks collect, big data has the ability to completely change business operations and procedures. Big Data analytics is the answer to the current banking environment's challenges of growing competitiveness, fraud, and cyber security risks.