Bundles Of Items Research Articles

Composite Retrieval of Diverse and Complementary Bundles

Users are often faced with the problem of finding complementary items that together achieve a single common goal (e.g., a starter kit for a novice astronomer, a collection of question/answers related to low-carb nutrition, a set of places to visit on holidays). In this paper, we argue that for some application scenarios returning item bundles is more appropriate than ranked lists. Thus we define composite retrieval as the problem of finding <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$k$</tex><mathgraphic fileref="bonchi-ieq1-2306678.gif" graphicformat="GIF"/> </formula> bundles of complementary items. Beyond complementarity of items, the bundles must be valid w.r.t. a given budget, and the answer set of <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$k$</tex> <mathgraphic fileref="bonchi-ieq2-2306678.gif" graphicformat="GIF"/></formula> bundles must exhibit diversity. We formally define the problem and show that in its general form is <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">${\bf NP}$</tex> <mathgraphic fileref="bonchi-ieq3-2306678.gif" graphicformat="GIF"/></formula> -hard and that also the special cases in which each bundle is formed by only one item, or only one bundle is sought, are hard. Our characterization however suggests how to adopt a two-phase approach (Produce-and-Choose, or PAC) in which we first produce many valid bundles, and then we choose <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$k$</tex><mathgraphic fileref="bonchi-ieq4-2306678.gif" graphicformat="GIF"/> </formula> among them. For the first phase we devise two ad-hoc clustering algorithms, while for the second phase we adapt heuristics with approximation guarantees for a related problem. We also devise another approach which is based on first finding a <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$k$</tex> <mathgraphic fileref="bonchi-ieq5-2306678.gif" graphicformat="GIF"/></formula> -clustering and then selecting a valid bundle from each of the produced clusters (Cluster-and-Pick, or CAP). We compare experimentally the proposed methods on two real-world data sets: the first data set is given by a sample of touristic attractions in 10 large European cities, while the second is a large database of user-generated restaurant reviews from Yahoo! Local. Our experiments show that when diversity is highly important, CAP is the best option, while when diversity is less important, a PAC approach constructing bundles around randomly chosen pivots, is better.

Consumer Choice and Aggregate Demand

Satisficing behavior is one of the most important subjects in consumer behavior studies. Satisficing consumers select any affordable bundle of items with utility larger than their satisfaction threshold. This contrasts to maximizing behavior, where the consumer selects the bundle of items with the highest possible utility within his or her budget constraint. Authors hypothesize that, all else equal, satisficers will purchase more goods overall when compared with maximizers. Furthermore, satisficers will also purchase more disposable rather than durable goods because they are less concerned with maximizing the total value of their purchases. To test these hypotheses, an agent-based model of consumer behavior has been developed that allows for decision making based on either satisficing or maximizing rules. Satisficer agents use a modified genetic algorithm to find a satisficing bundle. Maximizer agents apply dynamic programming to find the best bundle of items. The aggregated results of consumer agents' purchases support aforementioned hypotheses when consumers select from three types of products: 1) cheap disposable, 2) cheap durable, and 3) expensive durable. The hypotheses also hold when a more realistic set of items is constructed based on the common economic assumption that supply curves are upward sloping. In this latter case, consumers choose bundles from a total of 5 types of items, each of which differs in price, quality, and durability.

Examining Sources of DIF in Psychological and Educational Assessment Using Multilevel Logistic Regression

In the last three decades, important progress has been made toward more efficient statistical techniques for detecting Differential Item Functioning (DIF). However, the findings are scant when it comes to explaining DIF. Multilevel regression models can expand the knowledge of DIF causes, specifying a DIF parameter that varies randomly over items and testing hypotheses on sources of DIF shared by item bundles. The present study uses multilevel logistic regression to identify the item characteristics that could explain the presence of DIF in short tests or questionnaires, which are usually used in psychological and educational assessment. The usefulness of the approach is tested on measurements of the attitudes toward science of Spanish and English pupils obtained from the OECD Programme for International Student Assessment database.

Linguistic and content validation of a German-language PRO-CTCAE-based patient-reported outcomes instrument to evaluate the late effect symptom experience after allogeneic hematopoietic stem cell transplantation

PurposeThe aim of this sequential mixed methods study was to develop a PRO-CTCAE (Patient-Reported Outcomes version of the Common Terminology Criteria for Adverse Events)-based measure of the symptom experience of late effects in German speaking long-term survivors of allogeneic stem cell transplantation (SCT), and to examine its content validity. MethodsThe US National Cancer Institute's PRO-CTAE item library was translated into German and linguistically validated. PRO-CTCAE symptoms prevalent in ≥50% of survivors (n = 15) and recognized in its importance by SCT experts (n = 9) were identified. Additional concepts relevant to the symptom experience and its consequences were elicited. Content validity of the PROVIVO (Patient-Reported Outcomes of long-term survivors after allogeneic SCT) instrument was assessed through an additional round of cognitive debriefing in 15 patients, and item and scale content validity indices by 9 experts. ResultsPROVIVO is comprised of a total of 49 items capturing the experience of physical, emotional and cognitive symptoms. To improve the instrument's utility for clinical decision-making, questions soliciting limitations in activities of daily living, frequent infections, and overall well-being were added. Cognitive debriefings demonstrated that items were well understood and relevant to the SCT survivor experience. Scale Content Validity Index (CVI) (0.94) and item CVI (median = 1; range 0.75–1) were very high. ConclusionsQualitative and quantitative data provide preliminary evidence supporting the content validity of PROVIVO and identify a PRO-CTCAE item bundle for use in SCT survivors. A study to evaluate the measurement properties of PROVIVO and to examine its capacity to improve survivorship care planning is underway.

The Comparison of Effects in 3PL Model and 3PL Testlet Model on the TOEIC

Evaluating or measuring test takers’ language abilities is of central importance in the development of standardized language tests that foster meaningful assessment. The Test of English for International Communication(TOEIC) is a widely used standardized test to evaluate test takers’ receptive(reading and listening skills) and productive(writing and speaking skills) language abilities. Although item response theory(IRT) models usually provide satisfactory answers for measuring parameters of items and test takers, they do not always lead to the correct solution when systematic biases are ignored in estimating items and test takers. Due to the paucity of validation studies of the TOEIC, the present study only seeks to explore psychometric properties of items in the simulated TOEIC test in the context of IRT and testlet response theory (TRT). In order to accomplish this purpose, this study describes how a set of items, sharing the same contents in the listening comprehension part of the TOEIC, behaves under the two suggested models (3PL and 3PLT) with the test samples who enrolled in the TOEIC classes in the university in South Korea. Of 100 items on TOEIC listening comprehension session, 60 items (10 items for photographs, 30 items for question-response, 30 items for short conversion, and 30 items for short talks session, respectively) are clustered within each testlet which sometimes called item bundle. Results from this study may provide more precise, reliable, and valid information about estimates regarding items and examinees. Later, suggestions for future research are offered.

Decomposing combinatorial auctions and set packing problems

Combinatorial auctions allow bidders to bid on bundles of items rather than just on single items. The winner determination problem in combinatorial auctions is the problem of determining the allocation of items to bidders such that the sum of the accepted bid prices is maximized. This problem is equivalent to the well-known maximum-weight set packing problem. Even though these problems are NP-hard in general, they can be solved in polynomial time on instances whose associated item graphs have bounded treewidth (called structured item graphs). However, the tractability of determining whether for a given problem instance a structured item graph of fixed treewidth exists (and if so, computing one efficiently) was an open problem. In this article, we solve this problem by proving that deciding the existence of structured item graphs is computationally intractable, even for treewidth 3. Motivated by this unfavorable complexity result, we investigate other structural restrictions, and we show that the notion of hypertree decomposition, a well-studied measure of hypergraph cyclicity, turns out to be most useful here. Indeed, we show that the winner determination problem is solvable in polynomial time on instances whose dual auction hypergraphs have bounded hypertree width. Our solution method is based on encoding winner determination via a constraint satisfaction optimization problem and on exhibiting an algorithm to solve this latter problem efficiently for such structurally restricted instances. The class of tractable instances identified by our approach, while being efficiently recognizable, properly contains the class of instances having a structured item graph. Moreover, on the larger class, our method solves winner determination with the same asymptotic complexity as the best algorithm proposed in the literature for the subclass of structured item graphs. Hypertree decompositions can equally profitably be applied to the maximum-weight independent set problem, which is the dual problem of maximum-weight set packing.

Integration and Disruption Effects of Shape and Texture in Haptic Search

In a search task, where one has to search for the presence of a target among distractors, the target is sometimes easily found, whereas in other searches it is much harder to find. The performance in a search task is influenced by the identity of the target, the identity of the distractors and the differences between the two. In this study, these factors were manipulated by varying the target and distractors in shape (cube or sphere) and roughness (rough or smooth) in a haptic search task. Participants had to grasp a bundle of items and determine as fast as possible whether a predefined target was present or not. It was found that roughness and edges were relatively salient features and the search for the presence of these features was faster than for their absence. If the task was easy, the addition of these features could also disrupt performance, even if they were irrelevant for the search task. Another important finding was that the search for a target that differed in two properties from the distractors was faster than a task with only a single property difference, although this was only found if the two target properties were non-salient. This means that shape and texture can be effectively integrated. Finally, it was found that edges are more beneficial to a search task than disrupting, whereas for roughness this was the other way round.

Modeling profit sharing in combinatorial exchanges by network flows

In this paper we study the possibilities of sharing profit in combinatorial procurement auctions and exchanges. Bundles of heterogeneous items are offered by the sellers, and the buyers can then place bundle bids on sets of these items. That way, both sellers and buyers can express synergies between items and avoid the well-known risk of exposure (see, e.g., Cramton, Shoham, & Steinberg, Combinatorial Auctions, 2006). The reassignment of items to participants is known as the Winner Determination Problem (WDP). We propose solving the WDP by using a Set Covering formulation, because profits are potentially higher than with the usual Set Partitioning formulation, and subsidies are unnecessary. The achieved benefit is then to be distributed amongst the participants of the auction, a process which is known as profit sharing. The literature on profit sharing provides various desirable criteria. We focus on three main properties we would like to guarantee: Budget balance, meaning that no more money is distributed than profit was generated, no negative transfers, which guarantees to each player that participation does not lead to a loss, and the core property, which provides every subcoalition with enough money to keep them from separating. We characterize all profit distributions that satisfy these three conditions by a monetary flow network and establish a connection to the famous VCG payment scheme (Clarke in Public Choice 18:19ff, 1971; Groves in Econometrica 41:617–631, 1973; Vickrey in J. Finance 16:8–37, 1961) and the Shapley Value (Shapley in Kuhn & Tucker (Eds.), Contributions to the Theory of Games, vol. II, pp. 307–317, 1953). Finally, we introduce a novel profit sharing scheme based on scaling down VCG discounts using max-min fairness principles to achieve budget balance. It approximates the Shapley Value linearly in the number of bundles and can be computed efficiently.

A Synthesis of the Peer‐Reviewed Differential Bundle Functioning Research

The purpose of this article was to present a synthesis of the peer‐reviewed differential bundle functioning (DBF) research that has been conducted to date. A total of 16 studies were synthesized according to the following characteristics: tests used and learner groups, organizing principles used for developing bundles, DBF detection methods used, and types of bundles that indicated statistically significant DBF in the hypothesized direction on multiple occasions. The article concludes with a list of suggestions to individuals who conduct DBF research. For example, effect size guidelines should be established for interpreting the amount of DBF in bundles of items assessed with simultaneous item bias test (SIBTEST), given that it is the most commonly used DBF procedure. This would reduce our reliance on statistical significance testing. General effect size guidelines are needed as well as guidelines for special circumstances like small sample cases. Other useful suggestions are offered as well.

Online pricing for bundles of multiple items

Given a seller with $$k$$ types of items, $$m$$ of each, a sequence of users $$\{u_1, u_2,\ldots \}$$ arrive one by one. Each user is single-minded, i.e., each user is interested only in a particular bundle of items. The seller must set the price and assign some amount of bundles to each user upon his/her arrival. Bundles can be sold fractionally. Each $$u_i$$ has his/her value function $$v_i(\cdot )$$ such that $$v_i(x)$$ is the highest unit price $$u_i$$ is willing to pay for $$x$$ bundles. The objective is to maximize the revenue of the seller by setting the price and amount of bundles for each user. In this paper, we first show that a lower bound of the competitive ratio for this problem is $$\Omega (\log h+\log k)$$ , where $$h$$ is the highest unit price to be paid among all users. We then give a deterministic online algorithm, Pricing, whose competitive ratio is $$O(\sqrt{k}\cdot \log h\log k)$$ . When $$k=1$$ the lower and upper bounds asymptotically match the optimal result $$O(\log h)$$ .

Exploring differential bundle functioning in mathematics by gender: the effect of hierarchical modelling

Researchers interested in exploring substantive group differences are increasingly attending to bundles of items (or testlets): the aim is to understand how gender differences, for instance, are explained by differential performances on different types or bundles of items, hence differential bundle functioning (DBF). Some previous work has modelled hierarchies in data in this context or considered item responses within persons, but here we model the bundles themselves as explanatory variables at the item level potentially explaining significant intra-class correlation due to gender differences in item difficulty, and thus explaining variation at the second item level. In this study, we analyse DBF using single- and two-level models (the latter modelling random item effects, which models responses at Level 1 and items at Level 2) in a high-stakes National Mathematics test. The models show comparable regression coefficients but the statistical significances of the two-level models are smaller due to the larger values of the estimated standard errors. We discuss the contrasting relevance of this effect for test developers and gender researchers.

IS THERE ANY INTERACTION BETWEEN BACKGROUND KNOWLEDGE AND LANGUAGE PROFICIENCY THAT AFFECTS TOEFL IBT® READING PERFORMANCE?

ABSTRACTThis study investigated the effect of the interaction between test takers' background knowledge and language proficiency on their performance on the TOEFL iBT® reading section. Test takers with the target content background knowledge (the focal groups) and those without (the reference groups) were identified for each of the 5 selected passages based on their self‐identified academic and cultural backgrounds. The test takers were further classified into high and low proficiency groups based on their TOEFL iBT scores. Differential functioning was investigated at the item, item bundle, and passage levels. The results suggested that background knowledge interacted with language proficiency on certain items, which could be attributed to idiosyncratic passage and item characteristics (i.e., characteristics that were specific to a particular passage or item). Only 1 of the 5 passages investigated showed intermediate differential bundle functioning, favoring the focal group for both the high and low proficiency groups. There was no differential functioning at the passage level. This research sheds new light on our understanding of the effects of background knowledge and its interaction with language proficiency in the context of second language reading comprehension. It also has significant practical implications for test developers in advancing fair assessments.

Are Inferential Reading Items More Susceptible to Cultural Bias Than Literal Reading Items?

The purpose of this article is to illustrate a seven-step process for determining whether inferential reading items were more susceptible to cultural bias than literal reading items. The seven-step process was demonstrated using multiple-choice data from the reading portion of a reading/language arts test for fifth and seventh grade Hispanic, Black, and White examinees. The process began at the broadest level of analyzing bundles of items for differential bundle functioning and finished at the narrowest level of analyzing individual items for differential distractor functioning. Some evidence was found to indicate that inferential items are more susceptible to cultural bias than literal items. Implications of the results are discussed, and suggestions for item writers and test developers are given.

Preference Coalition Formation Scheme for Buyer Coalition Services with Bundles of Items

Coalition stability is a major requirement in coalition formation. One important problem to achieve stability in n-person game theories is the assumption that the preference of each buyer is publicly known. The coalition is said to be stable if there are no objection by any subset of buyers according to their publicly known preferences. However, such assumption is often unrealistic in typical real-life situations. Individual buyers often have private preferences and make their decisions according to their own preferences instead. This study proposes a novel preference coalition formation scheme for buyer coalition services that attempts to consider private preference of individual buyers within the buyer coalition process. The theoretical foundations of the study are rooted in the fields of multi-criteria decision making, human practical reasoning, and n-person game theories, from which we design an appropriate scheme for our proposed buyer coalition framework with emphasis on private preferences of individual buyers. The authors validate their proposed scheme with simulation software developed to demonstrate results of a variety of practical situations.

Budget-Constrained Auctions with Heterogeneous Items

In this paper, we present the first approximation algorithms for the problem of designing revenue optimal Bayesian incentive compatible auctions when there are multiple (heterogeneous) items and when bidders can have arbitrary demand and budget constraints. Our mechanisms are surprisingly simple: We show that a sequential all-pay mechanism is a 4 approximation to the revenue of the optimal ex-interim truthful mechanism with discrete correlated type space for each bidder. We also show that a sequential posted price mechanism is a O(1) approximation to the revenue of the optimal ex-post truthful mechanism when the type space of each bidder is a product distribution that satisfies the standard hazard rate condition. We further show a logarithmic approximation when the hazard rate condition is removed, and complete the picture by showing that achieving a sub-logarithmic approximation, even for regular distributions and one bidder, requires pricing bundles of items. Our results are based on formulating novel LP relaxations for these problems, and developing generic rounding schemes from first principles. We believe this approach will be useful in other Bayesian mechanism design contexts.

Adaptive bidding in combinatorial auctions in dynamic markets

Combinatorial auction, where bidders can bid on bundles of items, has been the subject of increasing interest in recent years. Although much research work has been conducted on combinatorial auctions, most has been focusing on the winner determination problem. A largely unexplored area of research in combinatorial auctions is the design of bidding strategies, in particular, those that can be used in open and dynamic markets in which market situation is generally constantly changing. Obviously, a good bidding strategy to be used in such realistic markets cannot be obtained by analytical methods, which require all market information be known before a solution can possibly be found. Machine learning based approaches are not completely appropriate, either, as an optimal strategy learned from one market generally no longer perform well when the market situation changes. In this paper, we propose a new adaptive bidding strategy for combinatorial auction-based resource allocation problem in such dynamic markets. A bidder adopting this strategy constantly perceives the market situation, and adaptively reviews and adjusts his bid determination, thus responding to the dynamic market in a timely manner. Experiment results show that agents adopting this adaptive bidding strategy perform very well, even without any prior knowledge about the market.

Item price information feedback in multiple unit combinatorial auctions: design issues

Combinatorial auctions allow bidders to bid on individual items or bundles of items. This enables bidders to take advantage of the synergy or complementarity in their valuations of bundles. However, the number of bundles or packages that a bidder could explore may be large making these auctions too complex. Therefore, a combinatorial auction is often run as an iterative auction involving a series of rounds that progressively lead to a final allocation. In each intermediate round, bids are submitted and then provisional winners are determined. A key element in each round is the provision of price feedback to guide bidders in subsequent rounds. This price feedback can focus on packages or on items. Item (also known as linear) pricing feedback schemes have been widely researched for combinatorial auctions on unique items (where packages consist of one or more unique items but not multiple amounts of any item). It has been observed that such item price schemes have performed reasonably well in a wide variety of auction markets. However, they have not yet been thoroughly tested for auctions where the allocation involves multiple units of different items. In this paper, we extend several item pricing designs to the case of multiple unit combinatorial auctions. We identify a set of performance criteria by which an auctioneer could assess the suitability of a design for their particular case. We then numerically compare the algorithms using an agent-based model. Based on the results, we draw some general conclusions about the strengths and limitations of different schemes.

Equivalence of Paper-and-Pencil and Online Administration Modes of the Statewide English Test for Students With and Without Disabilities

This study investigated whether scores obtained from the online and paper-and-pencil administrations of the statewide end-of-course English test were equivalent for students with and without disabilities. Score comparability was evaluated by examining equivalence of factor structure (measurement invariance) and differential item and bundle functioning analyses for the online and paper groups. Results supported measurement invariance between the online and paper groups, suggesting that it is meaningful to compare scores across administration modes. When the data were analyzed at both the item and item bundle (content area) levels, similar performance appeared between the online and paper groups.

USING AN ANALYTIC NETWORK PROCESS MODEL IN COMBINATORIAL AUCTIONS

Auctions are important market mechanisms for the allocation of goods and services. Auctions are preferred often to other common processes because they are open, quite fair, easiness to understand by participants, and lead to economically efficient outcomes. Design of auctions is a multidisciplinary effort made of contributions from economics, operations research, informatics, and other disciplines. Combinatorial auctions are those auctions in which bidders can place bids on combinations of items, called packages, rather than just individual items. The advantage of combinatorial auctions is that the bidder can more fully express his preferences. This is particular important when items are complements. The multiple evaluation criteria can be used. There are dependencies among sellers, buyers, criteria, bundles of items. A variety of feedback processes creates complex system of items. For the whole structure seems to be very appropriate Analytic Network Process (ANP) approach. The ANP method makes possible to deal systematically with all kinds of dependence and feedback in the system of items. By the ANP approach can be evaluated the preferences of bundles of items. Dynamic Network Process (DNP) as an extension of ANP can deal with time dependent priorities in combinatorial auctions. http://dx.doi.org/10.13033/ijahp.v1i2.47

Combinatorial Coalition Formation for multi-item group-buying with heterogeneous customers

A group-buying market may offer multiple items with non-additive values (i.e., items may be complementary or substitutable), to buyers who are often heterogeneous in their item valuations. In such a situation, the formation of buying groups should concentrate buyers for common items while taking into consideration buyers' heterogeneous preferences over item bundles. Also, it should permit non-uniform cost sharing among buyers in the same group, which benefits all buyers by drawing more group-buying participants. We introduce the concept of Combinatorial Coalition Formation (CCF), which allows buyers to announce reserve prices for combinations of items. These reserve prices, along with the sellers' price-quantity curves for each item, are used to determine the formation of buying groups for each item. Moreover, buyers in the same group may not necessarily all pay the same price. The objective of CCF is to maximize buyers' total surplus. Determining the optimal coalition configuration in CCF is NP-hard, and the stability of such a configuration relies on the cost sharing rule within each group. We thus propose a heuristic algorithm for CCF based on augmented greedy selections, along with a cost sharing rule satisfying certain stability properties. Simulation results show that our approximate algorithm generates fairly good solutions compared to the optimal results, and is greatly superior to a simpler distributed approach. Furthermore, our algorithm's performance is enhanced when items are complementary or strongly substitutable, especially in settings when the prices decrease either rapidly or slowly with the quantities. Evaluations of the sellers' revenue under CCF demonstrate that sellers should offer a more gradually decreasing price-quantity curve for complementary or strongly substitutable items, and a more abruptly decreasing curve for weakly substitutable items. In addition, sellers may benefit from greater sales generated by simpler price-quantity curves with fewer steps.