scholarly journals Exploratory data science for discovery and ex‐ante assessment of operational policies: Insights from vehicle sharing

Author(s):  
Tobias Brandt ◽  
Oliver Dlugosch
Sensors ◽  
2019 ◽  
Vol 19 (12) ◽  
pp. 2772 ◽  
Author(s):  
Aguinaldo Bezerra ◽  
Ivanovitch Silva ◽  
Luiz Affonso Guedes ◽  
Diego Silva ◽  
Gustavo Leitão ◽  
...  

Alarm and event logs are an immense but latent source of knowledge commonly undervalued in industry. Though, the current massive data-exchange, high efficiency and strong competitiveness landscape, boosted by Industry 4.0 and IIoT (Industrial Internet of Things) paradigms, does not accommodate such a data misuse and demands more incisive approaches when analyzing industrial data. Advances in Data Science and Big Data (or more precisely, Industrial Big Data) have been enabling novel approaches in data analysis which can be great allies in extracting hitherto hidden information from plant operation data. Coping with that, this work proposes the use of Exploratory Data Analysis (EDA) as a promising data-driven approach to pave industrial alarm and event analysis. This approach proved to be fully able to increase industrial perception by extracting insights and valuable information from real-world industrial data without making prior assumptions.


Author(s):  
M. Govindarajan

This chapter focuses on introduction to the field of data science. Data science is the area of study which involves extracting insights from vast amounts of data by the use of various scientific methods, algorithms, and processes. The term data science has emerged because of the evolution of mathematical statistics, data analysis, and big data. Data science helps to discover hidden patterns from the raw data. It enables to translate a business problem into a research project and then translate it back into a practical solution. The purpose of this chapter is to provide emphasis on integration and synthesis of concepts, techniques, applications, and tools to deal with various facets of data science practice, including data collection and integration, exploratory data analysis, predictive modeling, descriptive modeling, data product creation, evaluation, and effective communication.


2019 ◽  
Vol 27 (3) ◽  
pp. 233-251
Author(s):  
Sabeena Jalal ◽  
Marshall E Lloyd ◽  
Faisal Khosa ◽  
Grace I-Hsuan Hsu ◽  
Savvas Nicolaou

2021 ◽  
Author(s):  
Johanna Schmidt

Organizations are collecting an increasing amount of data every day. To make use of this rich source of information, more and more employees have to deal with data analysis and data science. Exploring data, understanding its structure, and finding new insights, can be greatly supported by data visualization. Therefore, the increasing interest in data science and data analytics also leads to a growing interest in data visualization and exploratory data analysis. We will outline how existing data visualization techniques are already successfully employed in different data science workflow stages. In some cases, visualization is beneficial, while still future research will be needed for other categories. The vast amount of libraries and applications available for data visualization has fostered its usage in data science. We will highlight the differences among the libraries and applications currently available. Unfortunately, there is still a clear gap between visualization research developments over the past decades and the features provided by commonly used tools and data science applications. Although basic charting options are commonly available, more advanced visualization techniques have hardly been integrated as new features yet.


Author(s):  
Sebastian Baunsgaard ◽  
Matthias Boehm ◽  
Ankit Chaudhary ◽  
Behrouz Derakhshan ◽  
Stefan Geißelsöder ◽  
...  

2018 ◽  
Vol 70 (5) ◽  
pp. 1844-1859
Author(s):  
Alber Sánchez ◽  
Lubia Vinhas ◽  
Gilberto Queiroz ◽  
Rolf Simoes ◽  
Vitor Gomes ◽  
...  

Author(s):  
Aniket M. Wazarkar

Python is an interpreted object-oriented programming language that is sustainably procuring vogue in the field of data science and analytics by fabricating complex software applications. Establishing a righteous nexus between developers and data scientists. Python has undoubtedly become paramount for data scientists mindful of cosmic and robust standard libraries which are used for analyzing and visualizing the data. Data scientists have to deal with the exceedingly large amount of data alias as big data. With elementary usage and a vast set of python libraries, Python has doubtlessly become an admired option to handle big data. Python has developed and evolved analytical tools which can help data scientist in developing machine learning models, web services, data mining, data classification, exploratory data analysis, etc. In this paper, we will scrutinize various tools which are used by python programmers for efficient data analytics, their scope with contrast to other programming languages.


2021 ◽  
Vol 1 (1) ◽  
pp. 32-40
Author(s):  
Amir Mahmud Husein ◽  
Fachrul Rozi Lubis ◽  
Muhammad Khoiruddin Harahap

Peramalan penjualan produk adalah aspek utama dari manajemen pembelian, persediaan yang melebihi permintaan atau kekurangan akan berdampak pada manajemen pelayanan maupun secara ekominis. Makalah ini fokus mencoba menyajikan penerapan analisis prediktif dengan mengadopsi kerangka kerja Data Science (ilmu data) untuk menemukan wawasan yang berguna dalam pengambilan keputusan bisnis khususnya tentang peramalan penjualan produk di masa depan. Kerangka CRISP-DM diusulkan dengan tahapan pemahasan bisnis, pemahaman dan persiapan data, exploratory data analysis (EDA) dan pemodelan. Berdasarkan hasil pengujian data penjualan yang dievaluasi berdasarkan RMSE dan MAE, algoritma XGBoost menghasilkan prediksi berada dalam 1,3% kemudian ARIMA sebesar 1.6%, masih lebih baik dibandingkan LinearRegression, RandomForestdan LSTM dengan tingkat kesalahan sebesar 1.81%, 1.97%, 2.21% pada masing-masing algoritma dari data aktual.


Sign in / Sign up

Export Citation Format

Share Document