Rodríguez Aguilar, Román
Thumbnail Image
Preferred name
Rodríguez Aguilar, Román
Official Name
Rodríguez Aguilar, Román
Alternative Name
rrodrigueza
Main Affiliation
ORCID
Scopus Author ID
56717663000
Researcher ID
AAO-6158-2020

Research Output
Now showing 1 - 2 of 2
No Thumbnail Available
Publication

Machine Learning for Digital Shadow Design in Health Insurance Sector

2024 , Rodríguez Aguilar, Román , Marmolejo Saucedo, José Antonio , Rodríguez-Aguilar, Miriam , Marmolejo-Saucedo, Liliana

The digital transformation process in organizations has accelerated significantly in recent years; the COVID-19 pandemic was a catalyst that highlighted the need for digitalization in all sectors. In the case of the health sector, this process is complex due to the processes inherent in health care as well as the integration of multiple sectors that allow the provision of health services. A first approach towards the construction of a Digital Twin in health organizations is a Digital Shadow that allows an orderly transition towards digital operation in real time. This paper presents a first approach to the design of a Digital Shadow for the health insurance sector and specifically for the care of patients diagnosed with COVID-19 through the implementation of an analytical intelligence system based on machine learning models to forecast and monitor to patients who represent catastrophic cases for the insurer. © 2024 Springer Nature

View
No Thumbnail Available
Publication

A machine learning-based analytical intelligence system for forecasting demand of new products based on chlorophyll : a hybrid approach

2024 , Rodríguez Aguilar, Román , Marmolejo Saucedo, José Antonio , Garcia-Llamas, Eduardo , Rodríguez-Aguilar, Miriam , Marmolejo-Saucedo, Liliana

This manuscript addresses the problem of forecasting the demand for innovative products with limited and inhomogeneous sales data over time. The main objective of the study is to use the information available from a group of innovative chlorophyll-based food products to build a coherent demand forecasting system. From a transactional database, time series were constructed for each group of products, analyzing the stationarity and seasonality of the time series through the Dickey–Fuller and Canova–Hansen tests. Likewise, an ARIMA model, a long short-term memory (LSTM) recurrent deep neural network, and a support vector machine (SVM) were trained to select the best model for each product based on a forecast performance metric. A comparison between classical forecasting techniques and machine learning models is shown. The LSTM neural network was the best model for most products because the internal architecture of the network allows not only to capture non-linear relationships between variables but is also capable of controlling the flow of information to preserve characteristics over time that are relevant for forecasts. The second-best model was the SVM, which allows capturing non-linear behaviors through kernel functions and uses a smaller amount of data for its estimation. Finally, the ARIMA model presented the lowest performance for all products. The objective of having various methodologies is that the system allows the best forecast to be selected according to the type of product, availability of information and methodology used, which will allow the company to integrate new products into the system over time. ©Springer

View