An interactive genetic algorithm with the interval arithmetic based on hesitation and its application to achieve customer collaborative product configuration design

Complex product configuration design requires rapid and accurate response to customers’ demand. The participation of customers in product design will be a very effective solution to achieve this. The traditional interactive genetic algorithm (IGA) can solve the above problem to some extent by a computer-aided user interface. However, it is difficult to adopt an accurate number to express an individual's fitness because the customers’ cognition of evolutionary population is uncertain, and to solve the users’ fatigue problem in IGA. Thus, an interactive genetic algorithm with interval individual fitness based on hesitancy (IGA-HIIF) is proposed in this paper. In IGA-HIIF, the interval number derived from users’ evaluation time is adopted to express an individual's fitness, and the evolutionary individuals are compared according to the interval probability dominant strategy proposed in this paper. Then, the genetic operations are applied to generate offspring population and the evolutionary process doesn’t stop until it meets the termination conditions of the evolution or user manually terminates the evolution process. The IGA-HIIF is applied into the design system of the car console configuration, and compared to the other two kinds of IGA. The extensive experiment results are provided to demonstrate that our proposed algorithm is correct and efficient.     

Mining customer requirements from online reviews: A product improvement perspective

Big data commerce has become an e-commerce trend. Learning how to extract valuable and real time insights from big data to drive smarter and more profitable business decisions is a main task of big data commerce. Using online reviews as an example, manufacturers have come to value how to select helpful online reviews and what can be learned from online reviews for new product development. In this research, we first proposed an automatic filtering model to predict the helpfulness of online reviews from the perspective of the product designer. The KANO method, which is based on the classical conjoint analysis model, is then innovatively applied to analyze online reviews to develop appropriate product improvement strategies. Moreover, an empirical case study using the new method is conducted with the data we acquired from JD.com, one of the largest electronic marketplaces in China. The case study indicates the effectiveness and robustness of the proposed approach. Our research suggests that the combination of big data and classical management models can bring success for big data commerce.     

An approach to competitive product line design using conjoint data

In today’s highly competitive environment, where market oriented firms aim to maximize profits through customer satisfaction, there is an increasing need to design a product line, rather than a single product. The main goal of designing a profit maximizing product line is to target the ‘right product’ to the ‘right customer’. Although conjoint analysis has turned out to be one of the most widely used techniques for product line design, it falls to explicitly consider retaliatory reactions from competitors. In this paper, we propose a new conjoint-based approach to competitive new product line design, employing the Nash equilibrium concept. The optimal product line design problem for each firm is formulated as a nonlinear integer programming problem. In the absence of a closed-form solution, to compute the Nash equilibrium and to determine the optimal product line, we propose a two-phase procedure: a sequential iterative procedure in the first phase, and backward induction in the second. To solve the optimization problem in each of the iterations of the sequential procedure, we used the branch-and-bound method. The proposed approach is illustrated under several scenarios of competition using previously published conjoint data.     

An in-process customer utility prediction system for product conceptualisation

Customer involvement in new product development, especially in the early stage of product conceptualisation, plays an important role for a successful product. In this study, a customer utility prediction system (CUPS) is proposed. The system comprises two modules, namely design knowledge acquisition module and customer utility evaluation module. In the design knowledge acquisition module, a knowledge acquisition technique called general sorting is utilised to establish a design knowledge hierarchy (DKH), in which design options can be generated. In the same module, customer voices towards diverse design options called customer-sensitive design criteria are solicited from customer requirements. Subsequently, in the customer utility evaluation module, a measurement for customer desirability, i.e. customer utility index (CUI), is formulated using conjoint analysis (CA) technique. Finally, the rated criteria are also used as inputs to a radial basis function (RBF) neural network for in-process customer utility prediction. A case study on cellular phone design is used to illustrate the proposed approach.     

Enhanced customer requirement classification for product design using big data and improved Kano model

The classification of customer requirements (CRs) has a significant impact on the solution of product design. Existing CRs classification methods such as the Kano model and IPA model are time-consuming and inaccurate. This paper proposes a CRs classification method for product design using big data of online customer reviews of products to classify CRs accurately and efficiently. Comments of customer reviews are matched to CRs using a hierarchical semantic similarity method. Customer satisfaction degrees are defined based on emotional levels of adjectives and adverbs of customer comments using word vectors. The function implementation degree of each product is determined by specifications crawled from online products. Fitting curves are formed by defined customer satisfaction and function implementation of CRs using polynomial modeling and least square methods. Based on the slope of the fitted curves, CRs are classified to provide the minimum and maximum function implementations of CRs in each CR group to guide a product design process. The proposed method is applied in a case study of defining CRs classifications for design of upper limb rehabilitation devices. For verifying the proposed method, CRs defined by the existing methods are compared with CRs from the proposed method in design of an upper limb rehabilitation device.     

A generic genetic algorithm for product family design

Product family design (PFD) has been well recognized as an effective means to satisfy diverse market niches while maintaining the economies of scale and scope. PFD essentially entails a configuration problem by “combination," where combinatorial explosion always occurs and is known to be mathematically intractable or NP-hard. Although genetic algorithms (GAs) have been proven to excel in solving combinatorial optimization problems, it is difficult to adopt the traditional GA to deal with the complex data and interrelationships inherent in the PFD problem. This paper proposes a generic genetic algorithm (GGA) for PFD. A generic encoding scheme is developed to adapt to diverse PFD scenarios. A hybrid constraint-handling strategy is proposed to handle complex and distinguishing constraints at different stages along the evolutionary process. The design and implementation procedures of the GGA are discussed in detail. An application of the proposed GGA to motor family design is reported. The GGA efficiency is also tested through efficiency analysis in terms of the probability of generating feasible solutions, as well as through analysis of the GGA complexity.     

Data management of green product development with generic modularized product architecture

Many manufacturers are facing a complex situation in the mixed production environment, in which green and non-green products are fabricated simultaneously. They are losing competitiveness as a downstream supplier due to lacking of a cost-effective approach to managing product variations compliant with different green directives. This paper presents a methodology based on generic modularized product architecture that facilitates data management of green product development. The four-level architecture allows one unified representation for multiple product models. An option control mechanism enables a quick generation of their BOMs (bills of material). A procedure consisting of seven steps is proposed to accomplish this. PDM functions are implemented to demonstrate the effectiveness of the methodology using a real LCD TV family as an example. This work complements the past studies on green product development, which mainly tackled the problem from design, process, and supply chain improvement. In contrast, from a management perspective, the proposed methodology provides a simple but useful tool for small-to-medium-sized enterprises (SMEs) to perform green product development in an economical manner.     

Dynamic modelling of customer preferences for product design using DENFIS and opinion mining

Previous studies mainly employed customer surveys to collect survey data for understanding customer preferences on products and developing customer preference models. In reality, customer preferences on products could change over time. Thus, the time series data of customer preferences under different time periods should be collected for the modelling of customer preferences. However, it is difficult to obtain the time series data based on customer surveys because of long survey time and substantial resources involved. In recent years, a large number of online customer reviews of products can be found on various websites, from which the time series data of customer preferences can be extracted easily. Some previous studies have attempted to analyse customer preferences on products based on online customer reviews. However, two issues were not addressed in previous studies which are the fuzziness of the sentiment expressed by customers existing in online reviews and the modelling of customer preferences based on the time series data obtained from online reviews. In this paper, a new methodology for dynamic modelling of customer preferences based on online customer reviews is proposed to address the two issues which mainly involves opinion mining and dynamic evolving neural-fuzzy inference system (DENFIS). Opinion mining is adopted to analyze online reviews and perform sentiment analysis on the reviews under different time periods. With the mined time series data and the product attribute settings of reviewed products, a DENFIS approach is introduced to perform the dynamic modelling of customer preferences. A case study is used to illustrate the proposed methodology. The results of validation tests indicate that the proposed DENFIS approach outperforms various adaptive neuro-fuzzy inference system (ANFIS) approaches in the dynamic modelling of customer preferences in terms of the mean relative error and variance of errors. In addition, the proposed DENFIS approach can provide both crisp and fuzzy outputs that cannot be realized by using existing ANFIS and conventional DENFIS approaches.     

Optimal platform investment for product family design

Existing models for developing modular product families based on a common platform are either too engineering oriented or too marketing centric. In this paper, we propose an intermediate modeling ground that bridges this gap by simultaneously considering essential concepts from engineering and marketing to construct an alternative model for platform-based product families. In this model, each variant (in the platform-based product family) contributes a percentage to overall market coverage inside a target market segment. The extent to which a specific variant contributes to market coverage is linked to its degree of distinctiveness. On the other hand the cost of development of all variants (that constitute the product family) is also dependent on the degree of commonality between these variants. The objective of the model is to maximize market coverage subject to an available development budget. Based on a conceptual design of the product family, the proposed model suggests the optimal initial investment in the platform, the commonality level between variants, and the number of variants to be produced in order to maximize market coverage using both analytical and simulation techniques. An application example using an ice scraper product family is included to demonstrate the proposed model.     

Relationship between meanings,emotions, product preferences and personal values. Application to ceramic tile floorings

This work aims to validate a conceptual framework which establishes the main relationships between subjective elements in human–product interaction, such as meanings, emotions, product preferences, and personal values. The study analyzes the relationships between meanings and emotions, and between these and preferences, as well as the influence of personal values on such relationships. The study was applied to ceramic tile floorings.     

Innovative product design based on customer requirement weight calculation model

In the processes of product innovation and design, it is important for the designers to find and capture customer's focus through customer requirement weight calculation and ranking. Based on the fuzzy set theory and Euclidean space distance, this paper puts forward a method for customer requirement weight calculation called Euclidean space distances weighting ranking method. This method is used in the fuzzy analytic hierarchy process that satisfies the additive consistent fuzzy matrix. A model for the weight calculation steps is constructed; meanwhile, a product innovation design module on the basis of the customer requirement weight calculation model is developed. Finally, combined with the instance of titanium sponge production, the customer requirement weight calculation model is validated. By the innovation design module, the structure of the titanium sponge reactor has been improved and made innovative.     

An integrated neuro-genetic approach incorporating the Taguchi method for product design

Product design is a multidisciplinary activity that requires the integration of concurrent engineering approaches into a design process that secures competitive advantages in product quality. In concurrent engineering, the Taguchi method has demonstrated an efficient design approach for product quality improvement. However, the Taguchi method intuitively uses parameters and levels in measuring the optimum combination of design parameter values, which might not guarantee that the final solution is the most optimal. This work proposes an integrated procedure that involves neural network training and genetic algorithm simulation within the Taguchi quality design process to aid in searching for the optimum solution with more precise design parameter values for improving the product development. The concept of fractals in computer graphics is also considered in the generation of product form alternatives to demonstrate its application in product design. The stages in the general approach of the proposed procedures include: (1) use of the Taguchi experimental design procedure, (2) analysis of the neural network and genetic algorithm process, and (3) generation of design alternatives. An electric fan design is used as an example to describe the development and explore the applicability of the proposed procedures. The results indicate that the proposed procedures could enhance the efficiency of product design efforts by approximately 7.8%. It is also expected that the proposed design procedure will provide designers with a more effective approach to product development.     

Human-centric design personalization of 3D glasses frame in markerless augmented reality

This paper presents a virtual try-on system based on augmented reality for design personalization of facial accessory products. The system offers several novel functions that support real-time evaluation and modification of eyeglasses frame. 3D glasses model is embedded within video stream of the person who is wearing the glasses. Machine learning algorithms are developed for instantaneous tracking of facial features without use of markers. The tracking result enables continuously positioning of the glasses model on the user’s face while it is moving during the try-on process. In addition to color and texture, the user can instantly modify the glasses shape through simple semantic parameters. These functions not only facilitate evaluating products highly interactive with human users, but also engage them in the design process. This work has thus implemented the concept of human-centric design personalization.     

Market segmentation and ideal point identification for new product design using fuzzy data compression and fuzzy clustering methods

In product design, various methodologies have been proposed for market segmentation, which group consumers with similar customer requirements into clusters. Central points on market segments are always used as ideal points of customer requirements for product design, which reflects particular competitive strategies to effectively reach all consumers’ interests. However, existing methodologies ignore the fuzziness on consumers’ customer requirements. In this paper, a new methodology is proposed to perform market segmentation based on consumers’ customer requirements, which exist fuzziness. The methodology is an integration of a fuzzy compression technique for multi-dimension reduction and a fuzzy clustering technique. It first compresses the fuzzy data regarding customer requirements from high dimensions into two dimensions. After the fuzzy data is clustered into marketing segments, the centre points of market segments are used as ideal points for new product development. The effectiveness of the proposed methodology in market segmentation and identification of the ideal points for new product design is demonstrated using a case study of new digital camera design.     

A methodology of developing product family architecture for mass customization

Mass customization, aiming at delivering an increasing product variety that best serves customer needs while keeping mass production efficiency, has recently received numerous attention and popularity in industry and academia alike. This paper presents a methodology of developing product family architecture (PFA) to rationalize product development for mass customization. Systematic steps are developed to formulate a PFA in terms of functional, technical and physical views. The diverse needs of customers are matched with the capabilities of a firm through systematic planning of modularity in three consecutive views. The development of a PFA provides a unifying integration platform to synchronize market positioning, commonality employment and manufacturing scale of economy across the entire product realization process. A case study in an electronics company is reported to illustrate the potential and the feasibility of PFA methodology.     

Multiple-platform based product family design for mass customization using a modified genetic algorithm

A successful product family design method should achieve an optimal tradeoff among a set of conflicting objectives, which involves maximizing commonality across the family of products with the prerequisite of satisfying customers’ performance requirements. Optimization based methods are experiencing new found use in product family design to resolve the inherent tradeoff between commonality and distinctiveness that exists within a product family. This paper presents and develops a 2-level chromosome structured genetic algorithm (2LCGA) to simultaneously determine the optimal settings for the product platform and corresponding family of products, by automatically varying the amount of platform commonality within the product family during a single optimization process. The single-stage approach can yield improvements in the overall performance of the product family compared with two-stage approaches, in which the first stage involves determining the best settings for the platform variables and values of unique variables are found for each product in the second stage. The augmented scope of 2LCGA allows multiple platforms to be considered during product family optimization, offering opportunities for superior overall design by more efficacious tradeoffs between commonality and performance. The effectiveness of the proposed approach is demonstrated through the design of a family of universal electric motors and comparison against previous work.     

A heuristic genetic algorithm for product portfolio planning

Product portfolio planning has been recognized as a critical decision facing all companies across industries. It aims at the selection of a near-optimal mix of products and attribute levels to offer in the target market. It constitutes a combinatorial optimization problem that is deemed to be NP-hard in nature. Conventional enumeration-based optimization techniques become inhibitive given that the number of possible combinations may be enormous. Genetic algorithms have been proven to excel in solving combinatorial optimization problems. This paper develops a heuristic genetic algorithm for solving the product portfolio planning problem more effectively. A generic encoding scheme is introduced to synchronize product portfolio generation and selection coherently. The fitness function is established based on a shared surplus measure leveraging both the customer and engineering concerns. An unbalanced index is proposed to model the elitism of product portfolio solutions.     

Economical green product design based on simplified computer-aided product structure variation

Environmental issues have become an imperative concern for most companies in relation to modern product development. Special procedures have to be taken during the product development process to comply with recent green directives. Product structure is recognized as a critical factor that provides effective means for reducing environmental impact in product end-of-life. However, most previous studies failed to leverage the vast latitude at the design stage due to the assumption of a fixed product structure. To overcome this deficiency, we propose a CAD-based approach that allows automatic variation of 3D product structure by means of changing the combination of parts, selecting the assembly method, and rearranging the assembly sequence. A computing scheme uses Genetic Algorithm (GA) techniques to produce an optimal product structure from the design alternatives generated by the approach. This corresponds to lower assembly/disassembly costs, while complying with specified recycling and recovering rates. The scheme also chooses a smaller set of parts that needs to be disassembled and determines an economical disassembly process. Implemented in a commercial CAD system, the test results demonstrated the effectiveness of this scheme in green product design in a cost-effective manner.     

A support vector regression based prediction model of affective responses for product form design

In this paper, a state-of-the-art machine learning approach known as support vector regression (SVR) is introduced to develop a model that predicts consumers’ affective responses (CARs) for product form design. First, pairwise adjectives were used to describe the CARs toward product samples. Second, the product form features (PFFs) were examined systematically and then stored them either as continuous or discrete attributes. The adjective evaluation data of consumers were gathered from questionnaires. Finally, prediction models based on different adjectives were constructed using SVR, which trained a series of PFFs and the average CAR rating of all the respondents. The real-coded genetic algorithm (RCGA) was used to determine the optimal training parameters of SVR. The predictive performance of the SVR with RCGA (SVR–RCGA) is compared to that of SVR with 5-fold cross-validation (SVR–5FCV) and a back-propagation neural network (BPNN) with 5-fold cross-validation (BPNN–5FCV). The experimental results using the data sets on mobile phones and electronic scooters show that SVR performs better than BPNN. Moreover, the RCGA for optimizing training parameters for SVR is more convenient for practical usage in product form design than the timeconsuming CV.     

Clustering retail products based on customer behaviour

The categorization of retail products is essential for the business decision-making process. It is a common practice to classify products based on their quantitative and qualitative characteristics. In this paper, we use a purely data-driven approach. Our clustering of products is based exclusively on the customer behaviour. We propose a method for clustering retail products using market basket data. Our model is formulated as an optimization problem which is solved by a genetic algorithm. It is demonstrated on simulated data how our method behaves in different settings. The application using real data from a Czech drugstore company shows that our method leads to similar results in comparison with the classification by experts. The number of clusters is a parameter of our algorithm. We demonstrate that if more clusters are allowed than the original number of categories is, the method yields additional information about the structure of the product categorization.