Advanced Data Science Models for Player Behavioral Prediction

2019 ◽  
pp. 109-140
Author(s):  
África Periáñez ◽  
Anna Guitart ◽  
Pei Pei Chen ◽  
Ana Fernández del Río
Keyword(s):  
Data Science ◽  
Science Models ◽  
Behavioral Prediction

scholarly journals Behaviour of the Customers of an Insurance Company

2020 ◽  
Vol 6 (12) ◽  
pp. 336-341
Author(s):  
Dr. ML Sharma C Narinder Kaur and Mayank Singhal
Keyword(s):  
Health Insurance ◽  
Data Science ◽  
Consumer Behaviour ◽  
Real Life ◽  
Research Paper ◽  
Insurance Company ◽  
Health Issues ◽  
Time Data ◽  
Insurance Sector ◽  
Science Models

In today’s world as health issues among people increases, people become more aware for the health insurance. It’s a positive thing for the health companies but as the no. of customers increases, it is come into light that people are not punctual for paying the premium of the policy. This paper helps the policy companies to highlight and point out the defaulters who haven’t paid their premium. Mostly people forget about it, and some of them not paying the premium on time. In this research paper, I tried to understand the consumer behaviour in Insurance sector. The main objective of this paper to identify customers behaviour of paying the policy premiums and will they pay their next premium on time or not. Even will they pay their premium or not irrespective of time. Data was collected by various sites and some previous years data of some policy companies. Frequencies, Tabulation and some Data Science models have been used for the analysis. The objective of this project is to summarize is to make a predicting algorithm that can be used in real life applications to derive meaningful and accurate prediction based on the various aspects of data that is accessed.

Big Data Science: Models and Approaches, Characteristics, Challenges, and Applications

2021 ◽  
pp. 157-196
Author(s):  
Riyanshi Gupta ◽  
Kartik Krishna Bhardwaj ◽  
Deepak Kumar Sharma
Keyword(s):  
Big Data ◽  
Data Science ◽  
Science Models

scholarly journals Defining Covid 19 containment zones using K-means dynamically

2020 ◽  
Author(s):  
Satish Chinchorkar
Keyword(s):  
Data Science ◽  
Feasible Solution ◽  
Hot Spot ◽  
Effective Vaccine ◽  
Accurate Information ◽  
Contagious Nature ◽  
Science Models ◽  
Number Of Patients ◽  
Micro Level ◽  
The Cost

Abstract In view of the rapid growth of Covid-19 pandemic, contagious nature of the disease and non-availability of effective vaccine; the only way available is to restrict the people’s movements from mixing in a mob. However imposing total lockdown may not be the feasible solution because it is not only counter-productive but also causes the destructive impact on day-to-day working, economy and convenience of people. Moreover total lockdown is at the cost of public freedom may cause people agitation. Therefore determining the micro-level, manageable quarantine zones for affected Corona positive patients and further focus to only on the identified zones can be the resolution. For this purpose the scope of the containment zones must be determined with unbiased, precise and agile manner to enforce the controls on these zones to prevent the spread of this contagious disease. The updated and accurate information about such hot-spot zones can be useful for government to effectively implement the measures by concentrating the efforts on the zones and for other citizens to alert such hot-spot zones. However the task of identifying and circumventing the precise affected zones is not easy because of the constantly changing status of the patients. As soon as number of patients are getting recovered (the cycle time is around 14 days), these quarantine zones need to be revised and reconfigured accordingly, which is in addition to constantly accumulation of the data of new patients. The size and locations of such zones (affected by Corona positive patients) is dynamic in nature, therefore it becomes impossible to frequently reconfigure it manually. Implementing the models such as K-means from Data Science is proposed to help the situation because the zones determined by Data Science models are reliable (fact-based and latest), economic (not much additional infrastructure required), easy to understand (clusters are well defined and visible), flexible (can be parameterized / configured), and unbiased (because there is no preconception while defining zones/ clusters).

scholarly journals Data Science in Unveiling COVID-19 Pathogenesis and Diagnosis: Evolutionary Origin to Drug Repurposing

2020 ◽  
Author(s):  
Jayanta Kumar Das ◽  
Giuseppe Tradigo ◽  
Pierangelo Veltri ◽  
Pietro H Guzzi ◽  
Swarup Roy
Keyword(s):  
Drug Discovery ◽  
Structure Prediction ◽  
Data Science ◽  
Drug Repurposing ◽  
In Silico Analysis ◽  
Future Research ◽  
Medical Practitioners ◽  
Road Map ◽  
Science Models ◽  
Novel Coronavirus

The outbreak of novel Coronavirus (SARS-COV-2 ) disease (COVID-19) in Wuhan has attracted worldwide attention. SARS-COV-2 known to share a similar clinical manifestation that includes various symptoms such as pneumonia, fever, breathing difficulty, and in particular, SARS-COV-2 also causes a severe in ammation state that leads to death. Consequently, massive and rapid research growth has been observed across the globe to elucidate the mechanisms of infections and disease progression in genotype and phenotype scale. Data Science is playing a pivotal role in in-silico analysis to draw hidden and novel insights about the SARS-COV-2 origin, pathogenesis, COVID-19 outbreak forecasting, medical diagnosis, and drug discovery. With the availability of multi-omics, radiological, biomolecular, and medical data urges to develop novel exploratory and predictive models or customise exiting learning models to t the current problem domain. The presence of many approaches generates the need for the systematic surveys to guide both data scientists and medical practitioners. We perform an elaborate study on the state-of-the-art data science method ologies in action to tackle the current pandemic scenario. We consider various active COVID-19 data analytics domains such as phylogeny analysis, SARS-COV-2 genome identication, protein structure prediction, host-viral protein interactomics, clinical imaging, epidemiological analysis, and most importantly (existing) drug discovery. We highlight types of data, their generation pipeline, and the data science models in use. We believe that the current study will give a detailed sketch of the road map towards handling COVID-19 like situation by leveraging data science in the future. We summarise our review focusing on prime challenges and possible future research directions .

scholarly journals DATA SCIENCE APPROACH FOR IT PROJECT MANAGEMENT

2019 ◽  
Vol 2 ◽  
pp. 51
Author(s):  
Janis Grabis ◽  
Bohdan Haidabrus ◽  
Serhiy Protsenko ◽  
Iryna Protsenko ◽  
Anna Rovna
Keyword(s):  
Project Management ◽  
Data Science ◽  
Monitoring And Evaluation ◽  
It Project Management ◽  
Key Factors ◽  
Science Models ◽  
Data Vector ◽  
Project Data ◽  
High Level ◽  
Project Life

Majority of the IT companies realized that ability to analyse and use data, could be one of the key factors for increasing of number of successful projects, portfolios, programs. Key performance indicators based on data analysis helps organizations be more prosperous in a long term perspective. Also, statistical data are very useful for monitoring and evaluation of project results which are very important for managers, delivery directors, CTO and others high level management of company. The Data Science methods could make more efficient project management in several of business problems. Analysis of historical data from the project life-cycle based on Data Science models could provide more efficient benefits for different stakeholders. Differential of the project data vector with target as an integral evaluation of the project success which allow for the complex correlations between separate features. Therefore, the influence of features importance and override creatures could be decreased on the target. This study propose new approach based on Data Science providing more efficient and accurately project management, taking into account best practices and project performance data.

scholarly journals Hydrologically Informed Machine Learning for Rainfall-Runoff Modelling: Towards Distributed Modelling

2020 ◽  
Author(s):  
Herath Mudiyanselage Viraj Vidura Herath ◽  
Jayashree Chadalawada ◽  
Vladan Babovic
Keyword(s):  
Machine Learning ◽  
Data Science ◽  
Model Building ◽  
Building Blocks ◽  
Great Success ◽  
Rainfall Runoff ◽  
Distributed Modelling ◽  
Science Models ◽  
Lumped Models ◽  
Rainfall Runoff Model

Abstract. Despite showing a great success of applications in many commercial fields, machine learning and data science models in general, show a limited use in scientific fields including hydrology. The approach is often criticized for lack of interpretability and physical consistency. This has led to the emergence of new paradigms, such as Theory Guided Data Science (TGDS) and physics informed machine learning. The motivation behind such approaches is to improve the physical meaningfulness of machine learning models by blending existing scientific knowledge with learning algorithms. Following the same principles, in our prior work (Chadalawada et al., 2020), a new model induction framework was founded on Genetic Programming (GP) namely Machine Learning Rainfall-Runoff Model Induction Toolkit (ML-RR-MI). ML-RR-MI is cable of developing fully-fledged lumped conceptual rainfall-runoff models for a watershed of interest using the building blocks of two flexible rainfall-runoff modelling frameworks (FUSE and SUPERFLEX). In this study, we extend ML-RR-MI towards inducing semi-distributed rainfall-runoff models. This effort is motivated by the desire to address the decreasing meaningfulness of lumped models which tend to particularly deteriorate within large catchments where the spatial heterogeneity of forcing variables and watershed properties are significant. Henceforth, our machine learning approach for rainfall-runoff modelling titled Machine Induction Knowledge-Augmented System Hydrologique Asiatique (MIKA-SHA) captures spatial variabilities and automatically induces rainfall-runoff models for the catchment of interest without any subjectivity in model selection. Currently, MIKA-SHA learns models utilizing the model building components of FUSE and SUPERFLEX. However, the proposed framework can be coupled with any internally coherent collection of building blocks. MIKA-SHA’s model induction capabilities have been tested on the Red Creek catchment near Vestry, Mississippi, United States. The resulted model architectures through MIKA-SHA are compatible with previously reported research findings and fieldwork insights of the watershed and are readily interpretable by hydrologists.

Sign in / Sign up

Export Citation Format

Share Document