Customer’s segmentation is used as a marketing differentiation tool which allows organizations to understand their customers and build differentiated strategies. This research focuses on a database from the SMEs sector in Colombia, the CRISP-DM methodology was applied for the Data Mining process. The analysis was made based on the PFM model (Presence, Frequency, Monetary Value), and the following grouping algorithms were applied on this model: k-means, k-medoids, and Self-Organizing Maps (SOM). For validating the result of the grouping algorithms and selecting the one that provides the best quality groups, the cascade evaluation technique has been used applying a classification algorithm. Finally, the Apriori algorithm was used to find associations between products for each group of customers, so determining association according to loyalty.
In general, the agricultural producing sector is affected by the diversity in supply, mostly from small companies, in addition to the rigidity of the demand, the territorial dispersion, the seasonality or the generation of employment related to the rural environment. These characteristics differentiate the agricultural sector from other economic sectors. On the other hand, the volatility of prices payed by producers, the high cost of raw materials, and the instability of both domestic and international markets are factors which have eroded the competitiveness and profitability of the agricultural sector. Because of the advance in technology, applications have been developed based on Artificial Neural Networks (ANN) which have helped the development of sales forecast on consumer products, improving the accuracy of traditional forecasting systems. This research uses the RNA to develop an early warning system for facing the increase in agricultural products, considering macro and micro economic variables and factors related to the seasons of the year.
Se presenta el concepto de deconstruccion del diseno como una herramienta analitica para el estudio de procesos etnomatematicos del diseno involucrados en artesanias que producen objetos tangibles, en particular aquel tipo de artesania cuya materia prima son las hojas o hilos de palma o de paja. La deconstruccion del diseno emerge como alternativa ante el problema metodologico de establecer estrategias para analizar diversos objetos artesanales que son producto del entrecruzado de palmas. Dicha herramienta analitica no pretende modelizar los procesos de diseno vinculados en la artesania sino dar una aproximacion a la estructura de estos. Se tomo como objeto de estudio para el desarrollo de dicho concepto las artesanias del municipio de Usiacuri ubicado en el norte de Colombia. Se espera que esta herramienta analitica sirva como alternativa metodologica para los etnomatematicos en el analisis de dicho tipo de artesanias.
In this paper the results of research are shown in which the response surface was applied with central composite design for estimating the values of flatness as shown and accepted by the quality department and production company of the Caribbean region, taking into account factors such as voltage control in the winding sheet and the coefficient of friction. Initially, a first-order model was proposed to estimate the variance of the error and consider a quantitative model that takes into account the effects of combination. The method of steepest descent is used to sequentially move the descent path, i.e., in the direction of the minimum response decrement, until a new interval near optimal experimentation. Subsequently, a model of higher order was developed using a central composite design with center points and stars, taking into account control other variables additional response flatness, such as the roughness and hardness of the sheets in a range of flexible and acceptable tolerances for the company through a canonical model, and that will be the focus of future research.
This study presents a comparative analysis of the management of innovation among family and non-family companies of the Graphic Communication Industry in Colombia. For which a questionnaire was applied in order to know the divergences in the innovation process carried out by these two types of organizations. From this, the methodology of Generalized Linear Models (MLG) was used and the Bayesian inference was used on the parameters of the model, analyzing the effect of the family business, the products that commercialize on the management of innovation in goods observed as a product tangible Obtaining in this way, the identification of some characteristics of innovation management and divergences with non-family companies, among them: a tendency towards the type of preferred innovation, the different sources and objectives to innovate, and the factors that hinder its process of innovation.