Deepti Aggrawal

Consumer behaviour-based innovation diffusion modelling using stochastic differential equation incorporating change in adoption rate

Bass innovation and diffusion model and many of its extended forms have been reported in marketing literature and applied successfully for predicting adoption curve of products from different segments of market. All these models assume that an adopter buys the product only once in his lifetime, however, this may not be true, because a consumer might buy the product more than once for his utility (repeat purchasing). Also, there can occur a situation that the consumer leaves the system without buying the product (balking). In this paper, we propose a diffusion model based on Ito’s type of stochastic differential equation with repeat purchasing and balking. It also incorporates the change-point concept, where the rate of product adoption per remaining potential adopter might change due to shift in marketing/promotional strategy, entry/exit of some of the competitors in the market. The applicability of the proposed model is illustrated using new product sales data.

Generalized Innovation Diffusion Modeling & Weighted Criteria Based Ranking

Research in the field of innovation diffusion has been based on modeling and understanding the differing behavior of adopters in marketplace. The acceptance of innovation depends upon how the information about the product has diffused in the social system. During products life cycle, adoption of the product takes place in the following manner; first the information about the product reaches the potential buyers and then from informed buyers the adoption takes place. First process can be termed as Product Awareness Process (PAWP) and the later one can be termed as Product Adoption Process (PADP). In this paper, we propose a generalized approach for innovation diffusion modeling that takes care of product awareness process and product adoption process as two separate scenarios (studied jointly) before the product is eventually bought by the user. Convolution of probability distribution function has been used to make the distinction between two processes. Furthermore, a set of five comparison criteria have been formulated and each criteria has been assigned different weights to rank the proposed models. Validation is done on two different consumer durables and results show that the weighted criteria approach is a very capable methodology for models comparison.

Fault severity based multi-release SRGM with testing resources

In today’s environment of global competition where each company is trying to prove itself better than its competitors the software developers have to come up with multiple releases in order to survive in the market. Each release offers some innovative performance enhancement or some new functionality that distinguishing itself from the past release. But enhancing the product and upcoming with successive releases puts a constant pressure on even the best organized engineering organizations. The reason being, up-grading a software application is a complex process. Upgrading a software introduces the risk that the new release will contain a bug, causing the program to fail. Therefore, to capture the effect of faults generated in the software with multiple releases, we have developed a multi release software reliability model in this paper. The model uniquely takes into account the faults of the current release and the remaining faults of just previous release. The multi release software reliability growth model treats the fault removal rate as a function of testing resources consumed. In addition, the model also incorporates the severity of faults and considers that hard faults are removed with different rate than the rate required to remove simple faults. The model developed is validated on real data set with software which has been released in the market with new features four times.

Optimal Introduction Timing Policy for a Successive Generational Product

Globalized economy has led firms to introduce new innovations in the market quite frequently. Optimal Introduction time is an important strategic decision for firms because an early introduction may not take off as customers; channel members and other required partners might not be receptive enough, on the other hand too late an entry results in loss of opportunity for the firm. The decision is even more critical when introducing successive generations over time. In this study, the authors have developed an analytical approach to help decide the optimal introduction time for successive generational product. The timing decision depends on whether firms push the product to market before competitors or invest more time in process & product design and improvement. The authors have examined the case where a firm introduces successive generations of a durable product for which demand is characterized by an innovation diffusion process. Results are supplemented by a numerical example.

Software Reliability Modeling with Impact of Beta Testing on Release Decision

Increased dependence of humans on technologies has made it necessary for developing the software with high reliability and quality. This has led to an increased interest of firms toward the development of software with high level of efficiency; which can be achieved by incorporating beta tests for improving and ensuring that the software is safe and completely free from errors. In a software release life cycle, beta testing is the last important step that software developers carry out before they launch new software. Beta testing is a unique testing process that helps software developers to test a software product in different environments before its final release in the market. In this chapter of the book, we develop a SRGM by inculcating the concept of beta testing in the fault removal process to account for situations that might occur when the software is used in diverse environments. This is done to evade the chances of system being failed in the field. Conducting beta tests results in enhancement of software reliability and has been widely acknowledged. Furthermore, we have developed an optimal scheduling model and showed the importance of beta test while determining the general availability time of the software and making the system more cost effective. For validating the accuracy and predictive capability of the proposed model, we analyzed it on real software data set.

An interactive approach to determine optimal launch time of successive generational product

Effective product launch and commercialisation are critical drivers of top performance for the firms; to which a strong product launch greatly improves the chances of success. Launch is often the single costliest step in new product development. Despite its importance, costs, and risks, product launch has been relatively under researched in the product literature. Determination of optimal launch time is especially critical for high-technology products, where the introduction of each successive generation of a product requires the firm to explicitly consider its impact on the demand for preceding generations. The timing of the launch (i.e., when the launch is conducted from the point of view of the company, the competition, and the customer) is just as important as whether the activities are performed. More managerial attention should be devoted to launch timing with respect to all of these viewpoints in order to improve the chances of success. This study identifies attributes such as speedy launch and cos...

Reliability Analysis for Upgraded Software with Updates

In today’s continuous fluctuation market scenario, no software comes in single version. Competition and survival requirement has led firms to come up with upgraded version of the parent software as soon as possible. Testing these software(s) for reliability has been a cumbersome task for their developers, and the task is all the more tedious when dealing with successive versions. Highly reliable software requires thorough debugging throughout the testing as well as in the operational phase, and as a consequence, the role of updating (patching) implicitly comes in picture. With patching, the overall testing period definitely increases, but it also results in enhanced usability and overall performance of the system. Consequently, a large number of firms are employing updating strategies to gain competitive advantage over its rival firms. These updates help the firms to look after any ambiguity (if present) and overcome the functional issues of the software. In this paper, making use of convolution methodology, we have proposed a mathematical approach for keeping a check on the reliability of the upgraded software incorporating the concept of update. The proposed model incorporates this varied aspect in the fault removal under multi-releases, and thereby a procedural approach based on differing performance during the testing and operational environment is the unique aspect of the article. Further to supplement the results, numerical analysis has been done on real software failure data.

Queuing theory-based innovation diffusion modelling incorporating change in adoption rate

Adoption has always been an important process to discuss among marketers. Major work in the field of innovation adoption has been based on theory of first purchase by consumers. Of late attention has also been given to multi-stage nature of diffusion process. There are practitioners who have verified adoption as multi-stage process (depending on awareness and motivation). Researchers have lately also understood the value of change in marketing strategy and other factors that often lead to change in the rate of adoption. In this paper, we have made use of this stage wise approach of market penetration along with change point concept, have developed a methodical approach based on infinite server queuing theory and predicted sales for consumer durables. Experimental results estimated on sales of two different consumer durables show that present proposal can depict the change in adoption rates and predict the behaviour of the product in more accurate manner.

Vulnerability Discovery Modelling for Software with Multi-versions

Security vulnerabilities have been of huge concern as an un-patched vulnerability can potentially permit a security breach. Vulnerability Discovery Modelling (VDM) has been a methodical approach that has helped the developers to effectively plan for resource allocation required to develop patches for problematic software releases; and thus improving the security aspect of the software. Many researchers have proposed discovery modelling pertaining to a specific version of software and talked about time window between the discovery (of vulnerability) and release of the patch as its remedy. In today’s cut throat and neck to neck competitive market scenario, when every firm comes up with the successive version of its previous release; fixing of associated susceptibilities in the software becomes a more cumbersome task. Based on the fundamental of shared code among multi-version software system, in this chapter of the book, we propose a systematic approach for quantification of number of vulnerabilities discovered. With the aim of predicting and scrutinising the loopholes the applicability of the approach has been examined using various versions of Windows and Windows Server Operating Systems.

A discrete innovation diffusion model incorporating change in the adoption rate

New products play a significant role in the success of firms concerned with the introduction of innovative products. Mathematical modeling that can describe the life cycle of these products can provide major contribution in their successful diffusion. The Bass model of innovation diffusion is a main representative of the diffusion models. Many modifications have been made to the model since its development to answer the changing needs and limitations. The model was developed in continuous time, which limits its application on many real life applications having discrete time data. Due to this reason a discrete version of this model was proposed by another author Hirota. The model was based on Riccatis equation in mathematics. Although the model can be solved to exact solution but it is difficult to modify this model further and solve to get the exact solution. Further, in practice the pace of diffusion varies not only because of the life cycle phase but due to many other variations such as changes in advertising strategies, little product modifications, competitive products etc. In marketing this concept can be termed as change point. In the present article, we propose an approach to model the diffusion process using a discrete logistic function whose exact solution can be obtained using probability generating function (PGF), incorporating the aforesaid change point concept. The model is validated on the real life data sets. Therefore, the proposed model provides accurate parameter estimates, making it possible to predict when a product can be launched.