China
Africa
Explore chapters and articles related to this topic
Artificial Neural Network Modeling
Published in Shyam S. Sablani, M. Shafiur Rahman, Ashim K. Datta, Arun S. Mujumdar, Handbook of Food and Bioprocess Modeling Techniques, 2006
Verification of the optimal ANN model. The performance of the optimal ANN model (2 hidden layers and 12 neurons in each hidden layer) was validated using a larger data set (72,400 data points generated in the normal range of Re′ and n using RFM) not previously used in the training of the ANN model. The optimal ANN predicted f with a mean relative error of 0.17%, a standard deviation in relative error of 0.20%, and a coefficient of determination of 1.000. The large data set was also used with the simplest ANN configuration of one hidden layer consisting of two neurons. This ANN configuration predicted the friction factor with a mean relative error of 0.50%, a standard deviation of relative error of 0.60%, and a coefficient of determination of 0.999.
Customer Mobile Behavioral Segmentation and Analysis in Telecom Using Machine Learning
Published in Applied Artificial Intelligence, 2022
Eman Hussein Sharaf Addin, Novia Admodisastro, Siti Nur Syahirah Mohd Ashri, Azrina Kamaruddin, Yew Chew Chong
The RFM model defined three attributes as follows: Recency is how recent a customer has purchased the product, Frequency is how frequent a customer purchased the product and Monetary is how much money is spent by a customer during a purchase. Tavakoli et al., (2018) noted that the RFM model promotes an efficient analysis for making marketing decisions to target the right customers and generate suitable strategies based on customer’s purchasing behavior. RFM analysis represents a behavioral-based model that captures customer’s profiles by means of their recency, frequency and monetary values that measures customer’s buying behavior whether it is continuous over time. (2018) stated that a scoring method is generated to evaluate the scores of the three variables stated. Furthermore, the score values are used to develop a customer segmentation model that is used in any clustering algorithm such as K-means algorithm.
Categorizing suppliers for development investments in construction: application of DEA and RFM concept
Published in Construction Management and Economics, 2018
Abdollah Noorizadeh, Kamran Rashidi, Antti Peltokorpi
To utilize the supplier pyramid for SD investment allocations, appropriate criteria for supplier categorization in the construction industry have to be defined. In the marketing literature, the RFM method is used as a segmentation technique to categorize customers into different groups based on their performance on each of the three variables, consisting of recency, frequency and monetary value (Zhang et al. 2015). The RFM method is one of the most effective techniques for quantifying the customer transaction history (e.g. Blattberg et al. 2008, p. 323, Zhang et al. 2015, Singh and Singh 2016). It utilizes routinely collected historical transaction data for optimal allocation of marketing resources to increase the overall profitability of customers. As a simple, easy and practical technique, RFM is mostly used for analysing customers’ value to define an appropriate and personalized customer relationship management. For example, Hu et al. (2013) utilize the sequential pattern-mining method framed with RFM to discover customers’ purchasing behaviour in a simulated environment, using large data sets. In another study, hotel guests are segmented into different profitability groups, employing the RFM technique in the tourism industry (Dursun and Caber 2016). Zhang et al. (2015) add a clumpiness variable to the RFM and test the new model’s merits, using customer data from a large North American retailer.
A multi layer recency frequency monetary method for customer priority segmentation in online transaction
Published in Cogent Engineering, 2023
Andreas Handojo, Nyoman Pujawan, Budi Santosa, Moses Laksono Singgih
One method that is often used in segmenting customers is the RFM method. The RFM model has several basic advantages such as simplicity in the implementation process so that the method can be implemented quickly (Kahan, 1998). Another advantage is that its simplicity of results and processes so that the decision makers can easily interpret the results of the model obtained (Marcus, 1998). This model is quite capable of capturing customer characteristics using only a relatively small amount of data (Kaymak, 2001). Therefore, the RFM model is commonly used in customer analysis and customer segmentation.