A Case Study of Innovation of an Information Communication System and Upgrade of the Knowledge Base in Industry by ESB, Artificial Intelligence, and Big Data System Integration

Self Cite

Data processing is crucial in the insurance industry, due to the important information that is contained in the data. Business Intelligence (BI) allows to better manage the various activities as for companies working in the insurance sector. Business Intelligence based on the Decision Support System (DSS), makes it possible to improve the efficiency of decisions and processes, by improving them to the individual characteristics of the agents. In this direction, Key Performance Indicators (KPIs) are valid tools that help insurance companies to understand the current market and to anticipate future trends. The purpose of the present paper is to discuss a case study, which was developed within the research project "DSS / BI HUMAN RESOURCES", related to the implementation of an intelligent platform for the automated management of agents' activities. The platform includes BI, DSS, and KPIs. Specifically, the platform integrates Data Mining (DM) algorithms for agent scoring, K-means algorithms for customer clustering, and a Long Short-Term Memory (LSTM) artificial neural network for the prediction of agents KPIs. The LSTM model is validated by the Artificial Records (AR) approach, which allows to feed the training dataset in data-poor situations as in many practical cases using Artificial Intelligence (AI) algorithms. Using the LSTM-AR method, an analysis of the performance of the artificial neural network is carried out by changing the number of records in the dataset. More precisely, as the number of records increases, the accuracy increases up to a value equal to 0.9987.

Section: Resultssupporting

confidence: 61%

Implementation of a Decision Support System and Business Intelligence Algorithms for the Automated Management of Insurance Agents Activities

Massaro¹,

Panarese²,

Gargaro³

et al. 2021

Self Cite

“…The goal of the proposed paper is the study of motion detection sensitivity results of a prototype video surveillance system # RNN Model construction model = Sequential() model.add (SimpleRNN(units=128, input_shape=(1, step), activation="relu", return_sequences=True)) model.add (SimpleRNN(units=64, activation="relu", return_sequences=True)) model.add (SimpleRNN(units=64, activation="relu") figure(figsize=(20,12) figure(figsize=(20,12) Below is illustrated a screenshot proving the correct implementation of the tables of the prototype platform. (3,9) * t[i]) number_of_late_deliveries = int(0.1 * random.randrange(0, 8) * np.cos(0.003 * random.randrange (1,8) * t[i]) + 0.5 * random.randrange(0, 1) * np.cos( 0.001 * random.randrange (3,8) * t[i])) velocita_chiusura_trattativa = 0.1 * random.randrange(0, 1) * np.sin(0.004 * random.randrange (5,9) (3,4) * t[i]) percentuale_incassato = 0.1 * random.randrange(0, 5) * np.cos(0.008 * random.randrange (2,9) * t[i]) + 0.3 * random.randrange(0, 2) * np.sin( 0.001 * random.randrange (3,9)…”

Section: Appendix A: Neural Network Algorithmsmentioning

confidence: 99%

“…* t[i]) + 0.1 * random.randrange(0, 2) * np.cos( 0.001 * random.randrange(3,6) * t[i]) attivita_completate_trattativa = int(0.1 * random.randrange(0, 9) * np.cos(0.007 * random.randrange(1, 7) * t[i]) + 0.8 * random.randrange(0, 3) * np.cos( 0.001 * random.randrange(3, 5) * t[i])) ratio_attivita_settore_completate_totale_attivita_completate = 0.1 * random.randrange(0, 3) * np.tan(0.009 * random.randrange(2, 7) * t[i]) + 0.7 * random.randrange(0, 4) * np.tan( 0.001 * random.randrange(3, 4) * t[i]) ratio_attivita_settore_non_completate_totale_attivita_non_completate = 0.1 * random.randrange(0, 4) * np.cos(0.006 * random.randrange(1, 8) * t[i]) + 0.2 * random.randrange(0, 8) * np.tan( 0.001 * random.randrange(3, 7) * t[i]) valutazione_rischio = 0.1 * random.randrange(0, 2) * np.sin(0.008 * random.randrange(2, 9) * t[i]) + 0.4 * random.randrange(0, 9) * np.cos( 0.001 * random.randrange(3, 4) * t[i]) referenze_acquisite = int(0.1 * random.randrange(0, 3) * np.cos(0.002 * random.randrange(5, 8) * t[i]) + 0.6 * random.randrange(0, 4) * np.sin( 0.001 * random.randrange(3, 9) * t[i])) variabilita_servizi_venduti = int(0.1 * random.randrange(0, 7) * np.sin(0.001 * random.randrange(1, 2) * t[i]) + 0.5 * random.randrange(0, 6) * np.sin( 0.001 * random.randrange(3, 8) * t[i])) order_processing_time = 0.1 * random.randrange(0, 6) * np.sin(0.003 * random.randrange(2, 3) * t[i]) + 0.4 * random.randrange(0, 3) * np.cos( 0.001 * random.randrange…”

mentioning

confidence: 99%

Data Mining Applied in Food Trade Network

Massaro¹,

Dipierro²,

Saponaro³

et al. 2020

Self Cite

The proposed study deals with the design and the development of a Decision Support System (DSS) platform suitable for the global distribution system (GDS). Precisely, the prototype platform combines artificial intelligence and data mining algorithms to process data collected into a Cassandra Big Data system. In the first part of the paper platform architectures together with all the adopted frameworks including Key Performance Indicators (KPIs) definitions and risk mapping design have been discussed. In the second part data mining algorithms have been applied in order to predict main KPIs. The adopted artificial neural networks architectures are Long Short-Term Memory (LSTM), standard Recurrent Neural Network (RNN) and Gated Recurrent Units (GRU). A dataset with KPIs has been generated in order to test the algorithms. All performed algorithms show a good matching with the generated dataset, thus proving to be the correct approach to predict KPIs. The best performances in terms of Accuracy and Loss are reached by using the standard RNN. The proposed platform represents a solution to increase the Knowledge Base (KB) for a strategic marketing and advanced business intelligence operations.

“…So, the software and licenses used in research projects (indicated in Fig. 2 by SW) therefore become essential elements for structuring a knowledge base from which to implement an advanced BI necessary for the revisitation and the innovation of processes and services [27].…”

Section: Development Of the Project Specifications By Following Frascmentioning

confidence: 99%

A Case Study of Research Improvements in an Service Industry Upgrading the Knowledge Base of the Information System and the Process Management: Data Flow Automation, Association Rules and Data Mining

Massaro¹,

Lisco²,

Lombardi³

et al. 2019

Self Cite

In this paper is analyzed a case study of an upgrade of an industry communication system developed by following 'Frascati' research guidelines. The goal of the proposed model is to enhance the industry knowledge Base-KB-by acting directly on information communication system improvements and data system integration, enabling automated process and data processing. The paper follow all the steps performed during the project development: the preliminary data infrastructure design, the information infrastructure improvements, and data processing. Data processing is performed by a calculus engine embedding data mining association rules and Artificial Neural Network-ANN-predictive algorithms thus improving the research. The calculus engine has been implemented by a multiple variables model where the contract data are preliminary processed in order to define functions classifying the operation processes and activating automatically the service process management. The business intelligence-BI-operations are performed mainly by the calculus engine optimizing industry performances. The goal of the paper is to show how research and development-R&D-can be applied by gaining and optimizing the knowledge and processes of an Italian industry working in car services. The project has been developed with the collaboration of the industry ACI Global working in roadside assistance services. By means of a research project resources, the information technology-IT-infrastructure has been improved by new solutions of the communication system and of the data transfer. The proposed case of study provides a model and a guideline to follow in order to apply research in industry acting directly on data and information network.