Abstract:This article presents a model of the design and introduction of a product line when the firm is uncertain about consumer valuations for the products. We find that product line introduction strategy depends on this uncertainty. Specifically, under low levels of uncertainty the firm introduces both models during the first period; under higher levels of uncertainty, the firm prefers sequential introduction and delays design of the second product until the second period. Under intermediate levels of uncertainty th… Show more
“…A second related literature assumes that firms know demand only up to a parameter [Rothschild, 1974, Lodish, 1980, Aghion et al, 1991, Braden and Oren, 1994, Kalyanam, 1996, Biyalogorsky and Gerstner, 2004, Bergemann and Valimaki, 1996, Aviv and Pazcal, 2002, Hitsch, 2006, Desai et al, 2010, Bonatti, 2011, Biyalogorsky and Koenigsberg, 2014. The modeling approach in these papers assumes that the manager knows the structure of demand and just learns the parameters.…”
Section: Literature On Pricingmentioning
confidence: 99%
“…The modeling approach in these papers assumes that the manager knows the structure of demand and just learns the parameters. This could be a two-period model [Biyalogorsky and Koenigsberg, 2014] or an infinite-time model [Aghion et al, 1991]. In the infinitetime model, Aghion et al [1991] consider a very general model where the manager knows the structure of demand up to a parameter (θ), the firms sets prices and observes market outcomes.…”
Consider the pricing decision for a manager at a large online retailer, that sells millions of products.A manager must decide on real-time prices for each of these products. It is infeasible to have complete knowledge of demand curve for each product. A manager can run price experiments to learn about demand and maximize long run profits. There are two aspects that make this setting different from traditional brick-and-mortar settings. First, due to the number of products the manager must be able to automate pricing. Second, an online retailer can make frequent price changes. In this paper, we propose a dynamic price experimentation policy where the firm has incomplete demand information.For this general setting, we derive a pricing algorithm that balances earning profit immediately and learning for future profits. The proposed approach combines multi-armed bandit (MAB) algorithms statistical machine learning with partial identification of consumer demand from economic theory. Our automated policy solves this problem using a scalable distribution-free algorithm. We show that our method converges to the optimal price faster than standard machine learning MAB solutions to the problem. In a series of Monte Carlo simulations, we show that the proposed approach perform favorably compared to methods in computer science and revenue management.
“…A second related literature assumes that firms know demand only up to a parameter [Rothschild, 1974, Lodish, 1980, Aghion et al, 1991, Braden and Oren, 1994, Kalyanam, 1996, Biyalogorsky and Gerstner, 2004, Bergemann and Valimaki, 1996, Aviv and Pazcal, 2002, Hitsch, 2006, Desai et al, 2010, Bonatti, 2011, Biyalogorsky and Koenigsberg, 2014. The modeling approach in these papers assumes that the manager knows the structure of demand and just learns the parameters.…”
Section: Literature On Pricingmentioning
confidence: 99%
“…The modeling approach in these papers assumes that the manager knows the structure of demand and just learns the parameters. This could be a two-period model [Biyalogorsky and Koenigsberg, 2014] or an infinite-time model [Aghion et al, 1991]. In the infinitetime model, Aghion et al [1991] consider a very general model where the manager knows the structure of demand up to a parameter (θ), the firms sets prices and observes market outcomes.…”
Consider the pricing decision for a manager at a large online retailer, that sells millions of products.A manager must decide on real-time prices for each of these products. It is infeasible to have complete knowledge of demand curve for each product. A manager can run price experiments to learn about demand and maximize long run profits. There are two aspects that make this setting different from traditional brick-and-mortar settings. First, due to the number of products the manager must be able to automate pricing. Second, an online retailer can make frequent price changes. In this paper, we propose a dynamic price experimentation policy where the firm has incomplete demand information.For this general setting, we derive a pricing algorithm that balances earning profit immediately and learning for future profits. The proposed approach combines multi-armed bandit (MAB) algorithms statistical machine learning with partial identification of consumer demand from economic theory. Our automated policy solves this problem using a scalable distribution-free algorithm. We show that our method converges to the optimal price faster than standard machine learning MAB solutions to the problem. In a series of Monte Carlo simulations, we show that the proposed approach perform favorably compared to methods in computer science and revenue management.
“…When the levels of demand uncertainty are different, Biyalogorsky and Oded () show that different sequential introduction strategies should be used. Simultaneous introduction should be used only when the level of demand uncertainty is low.…”
We investigate an incumbent's optimal sequential introduction of new products over two periods in a competitive duopoly setting. The firm would like to preempt and counter competition from a future entrant. Alternatively, the firm should consider that one of its products might decrease sales for another of their products, a threat commonly known as cannibalization. In this paper, we examine three sequential introduction strategies. We find that a firm's optimal introduction sequence is governed by pressures from competition and cannibalization in the market. In general, competition has greater impact on firms’ profits than cannibalization. Introducing a high‐end product before a low‐end product can alleviate cannibalization for a weak entrant. In particular, the profit loss caused by competition is greater than that caused by cannibalization. When competition is intense, firms should consider alleviating the profit loss from competition over cannibalization by introducing a low‐end product before a high‐end product. In that case, the incumbent's high‐end product's quality must be no lower than the entrant's quality but the profit is derived mostly from the mark‐up on the low‐end product. Much of the high‐end product's profit is sacrificed in order to maximize profit from the entire product line. When cannibalization is intense and competition is mild (due to a weak entrant), the incumbent's profit gap between the high‐end and low‐end products is high. In that case, the firm can no longer afford to sacrifice its high‐end products’ profit and the order of introduction reverses.
“…In their paper they considered only a single product. Biyalogorsky and Koenigsberg (2010) extended the study to a product family and showed that when introducing a product line, the optimal introduction sequence depends on the level of demand uncertainty.…”
Section: Introductionmentioning
confidence: 98%
“…The literature in Economics and Marketing also studies product design under demand uncertainty (see Chatterjee andSugita 1990, Biyalogorsky andKoenigsberg 2010). Chatterjee and Sugita (1990) focus on the way demand uncertainty affects competitive new-product introductions.…”
A product family refers to a group of products that have been derived from a common product platform and which are specifically designed to satisfy a variety of market segments. In this paper, we consider a firm utilising product family design in order to respond to the requirements of two consumer segments, each characterised by different quality valuations. Although the total number of consumers in the market is known, the proportions each segment share are random, with known mean and variance. We show how the uncertainty of the market segmentation affects the firm's decision whether to use common rather than unique components. Motivated by a problem faced by a major automotive manufacturer, we study the consequence of low and high uncertainty, various product quality levels and the difference of marginal valuation on the best configuration.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.