China
Africa
Explore chapters and articles related to this topic
Smart cities and buildings
Published in Pieter Pauwels, Kris McGlinn, Buildings and Semantics, 2023
Hendro Wicaksono, Baris Yuce, Kris McGlinn, Ozum Calli
Predictive analytics focuses on predicting or forecasting future events or trends based on the patterns and correlations of data collected from the past. Statistical analysis and machine learning are typically employed to carry out predictive analytics. For example, a machine learning technique, multiple kernel regression (MKr), that extends support vector regression (SVR), is used to predict water demand in a city by considering water consumption and climate data such as temperature, wind speed, precipitation, and air pressure [173]. A decision tree based technique is also used to detect anomalies and predict energy consumption in buildings [179,413]. Zero-shot machine learning is proposed to estimate the flow of the urban transportation network [227].
IoT, Big Data, and Analytics
Published in Vijay Kumar, Mangey Ram, Predictive Analytics, 2021
Priyanka Vashisht, Vijay Kumar, Meghna Sharma
Descriptive analytics offers analysts key metrics and business measures. While diagnostic analytics helps in identifying the root cause of the problem [24, 25], both diagnostic and descriptive analytics facilitate the creation of a narrative of the past. Predictive analytics forecasts the possibility of certain occurrences that are likely to happen in the future, while prescriptive analytics helps in determining the best action an organization/individual can take. Prescriptive and predictive analytics assist in framing the future. In comparison to descriptive and predictive analytics, prescriptive analytics is not explored much [26]. Recently, many researchers are focusing on predictive and prescriptive analytics [27]. Predictive and prescriptive analytics use the statistical or optimization models for decision making well before the results, which leads to better business [26, 28]. New information and communication technologies, such as real-time streaming, sensor data, and IoT, have strengthened predictive analytics by providing businesses with probabilistic recommendations that facilitate effective decision making.
Compulsion for Cyber Intelligence for Rail Analytics in IoRNT
Published in Vijayalakshmi Saravanan, Alagan Anpalagan, T. Poongodi, Firoz Khan, Securing IoT and Big Data, 2020
Nalli Vinaya Kumari, G.S. Pradeep Ghantasala, M. Arvindhan
Predictive analytics is the next step in data reduction. Analysis of past data habits and developments will tell what could occur in the organization’s future. It leads to real business goals, efficient preparation, and aspirations of elimination. Predictive analytics are used by businesses to research the data and to find the answers to the search. Predictive analytics attempts to forecast the possibility of a potential event through several mathematical and ML algorithms, but prediction accuracy is not 100%, because it is dependent on probabilities. Algorithms use the data and fill the missing data with the best estimates to make predictions. The data is collected using CRM, POS, ERP, and HR historical data to evaluate data patterns and relations among different data set variables. Companies should focus on recruiting strategic experts, selecting ML algorithms for quantitative modelling, and implementing a successful organizational strategy.
Value creation from analytics with limited data: a case study on the retailing of durable consumer goods
Published in Journal of Decision Systems, 2023
Konstantin Hopf, Andreas Weigert, Thorsten Staake
Yet, research and practice lack knowledge on how firms that are not blessed with large amounts of data could also benefit from analytics. From the three broad areas of data analytics – descriptive, predictive, and prescriptive analytics (LaValle et al., 2011; Sivarajah et al., 2017), predictive analytics (with ML as the core technique) today seems to be the most powerful for firms in ‘successfully competing with business analytics’ (Kraus et al., 2020, p. 628). Predictive analytics is the main principle of advanced data analytics (Donoho, 2017; Kitchens et al., 2018). It makes use of ‘statistical models and other empirical methods that are aimed at creating empirical predictions (as opposed to predictions that follow from theory only), as well as methods for assessing the quality of those predictions in practice (i.e. predictive power)’ (Shmueli & Koppius, 2011, p. 554). As predictive analytics uses empirical data to create models, it particularly suffers from limited data. Therefore, we focus on this area of analytics and examine the following research question:
Predictive HR analytics and talent management: a conceptual framework
Published in Journal of Management Analytics, 2021
R. Navodya Gurusinghe, Bhadra J. H. Arachchige, Dushar Dayarathna
Level four is predictive analytics. Predictive analytics provides potential impact and thereby enable firms to make better decisions. In this stage, it is possible to conduct scenario planning by forecasting what is most likely to happen in future, by extending the capacity and capability of predictive analytics support firms to mitigate risks effectively. Applying predictive analytics in talent management will make firms enable to identify future talent shortage if any, identify high potential talent, develop a talent pipeline, identify critical positions in the organisation and the like. At this stage, the firm needs more physical resources such as programming tools like an open-source system like ‘R’ for statistical computation and visualisation and human resources such as dedicated data scientists for HR analytics. Once the firm reaches this level of predictive analytics, HR plays a significant role in strategic decision table of the firm as the top management is aware of the impact that PHRA create in their business outcomes. Firms who achieve this level of PHRA are more likely to observe a Chief Human Resources Officer (CHRO) in their board of directors or a people analytics centre of excellence that directly reports to the Chief Executive Officer (CEO) (Academy to Innovate HR, n.d.). In summary, an organisation can work continuously to build its PHRA capability from its operational reporting level, acquiring required resources as well as driving a data-driven culture in the organisation.
Big data supply chain analytics: ethical, privacy and security challenges posed to business, industries and society
Published in Production Planning & Control, 2022
Nnamdi Johnson Ogbuke, Yahaya Y. Yusuf, Kovvuri Dharma, Burcu A. Mercangoz
However, despite the impacts of these disruptive technologies, it required guidance and interpretation by people who knew the tools as well as the business, including the supply chain operators. According to Lamba and Singh (2017), big data provided limited real-time applications in the context of functional areas of operations and supply chain management such as procurement, production, logistics and forecasting. In addition, the author argued that there are certain barriers to implementing predictive analytics, such as the lack of skilled professionals, lack of awareness and dearth of tools for training the next generation of data scientists in the supply chain industry.