1,720,971 research outputs found
Dynamic optimization under uncertainty: Applications in engineering, manufacturing, and retail.
No full textL'abstract è presente nell'allegato / the abstract is in the attachmen
On the value of multi-echelon inventory management strategies for perishable items with on-/off-line channels
Get PDFThe progress of digitization makes the integration of online and offline sales channels increasingly necessary for retailers. Multichannel and omnichannel multi-echelon networks are gradually more common in responding to customer demands, but their complexity makes the optimization of replenishment and item allocation policies among different channels challenging, especially if products have a short shelf life, as in the case of food retailers, where customer behavior (e.g., first-/last- in-first-out selection) also plays a role. It is not always possible to solve this problem exactly and heuristics are required. We propose a dynamic model and jointly optimize allocation and replenishment policies in the case of perishable goods with stochastic demand, uncertainty in customer selection preferences, and fixed lead times. We study complexity and structure of optimal policies. Furthermore, we explore several intuitive generalizations of base-stock policies over multi-echelon networks, analyzing the effect that potential correlations and imbalances in demand volumes across channels generate on the heuristics and identifying the pros and cons of such solutions. Results show that inventory-pooling effects in multi-echelon models for perishable items are often combined with the allocation of fresher products to offline channels. Generalizations of the well-known constant-order or base-stock policies can be a viable solution that generates benefits and increases system flexibility. They advantageously leverage negative channel correlation, but in the case of unbalanced demand distributions, increased offline demand can impoverish the quality of some heuristics
Risk-averse Approaches for a Two-Stage Assembly-to-Order Problem
Get PDFAssembly to order is a production strategy where components are manufactured under demand uncertainty and end items are assembled only after demand is realized. Risk-neutral approaches aim to maximize the expected profit. However, this approach may fail if heavy-tailed or multi-modal distributions are likely to generate significant disruptions or if the shrinking life of products is considered. Conversely, risk-averse models may tackle these problems. In the paper, we deal with an assembly-to-order problem, modeled as a two-stage stochastic linear programming problem considering the introduction of a classical risk measure from finance: the conditional value-at-risk. We examine the characteristics and the performance of the model by means of a large number of out-of-sample scenarios
Early portfolio pruning: a scalable approach to hybrid portfolio selection
Get PDFDriving the decisions of stock market investors is among the most challenging financial research problems. Markowitz’s approach to portfolio selection models stock profitability and risk level through a mean–variance model, which involves estimating a very large number of parameters. In addition to requiring considerable computational effort, this raises serious concerns about the reliability of the model in real-world scenarios. This paper presents a hybrid approach that combines itemset extraction with portfolio selection. We propose to adapt Markowitz’s model logic to deal with sets of candidate portfolios rather than with single stocks. We overcome some of the known issues of the Markovitz model as follows: (i) Complexity: we reduce the model complexity, in terms of parameter estimation, by studying the interactions among stocks within a shortlist of candidate stock portfolios previously selected by an itemset mining algorithm. (ii) Portfolio-level constraints: we not only perform stock-level selection, but also support the enforcement of arbitrary constraints at the portfolio level, including the properties of diversification and the fundamental indicators. (iii) Usability: we simplify the decision-maker’s work by proposing a decision support system that enables flexible use of domain knowledge and human-in-the-loop feedback. The experimental results, achieved on the US stock market, confirm the proposed approach’s flexibility, effectiveness, and scalability
Pulsed electrodeposition of palladium nano-particles on coated multi-walled carbon nanotubes/nafion composite substrates: Electrocatalytic oxidation of hydrazine and propranolol in acid conditions
No full textThe palladium species were deposited on the multi-walled carbon nanotubes dispersed in nafion membrane by pulsed electrodeposition technique. The resulting modified electrode was defined CNT-Pd. The Pd electrodeposition was carried out in 50Â mM H2SO4 solution containing 4.0Â mM Pd(NO3)2 using a double pulse sequence of potentials: E1Â =Â â0.4Â V vs SCE (t1Â =Â 0.03Â s) and E2Â =Â 0.4Â V vs SCE (t2Â =Â 3Â s). SEM analysis showed a well-efficient distribution of Pd nanoparticles dispersed along the nanotubes randomly oriented in the nafion matrix. A surface loading of electrodeposited Pd species comprised between 2.0Â nmol and 2.5Â nmol was generally observed. The prepared electrode is useful to catalyze the electrooxidation of hydrazine and propranolol. The electroanalytical properties of the electrode were evaluated by cyclic voltammetry (CV) and differential pulse voltammetry (DPV). Under optimized DPV conditions, the CNT-Pd electrode exhibits interesting analytical performance in terms of linear range of concentrations, low detection limits (i.e., 8Â Î1⁄4M and 2Â Î1⁄4M for hydrazine and propranolol, respectively) and good temporal stability of the responses (i.e., 4%â5%)
Pulsed electrochemical deposition of nickel oxides on multi-walled carbon nanotubes from EDTA alkaline solutions: a SEM, XPS, and voltammetric characterization
Get PDFA study regarding the electrodeposition of nickel oxide particles on the activated multi-walled carbon nanotubes from 2 M NaOH solution containing Ni(NO3)2 and EDTA was carried out. The electrodeposition process was carried out using an optimized double-pulse sequence of potentials: E1 = â0.2 V vs. SCE (t1 = 0.3 s) and E2 = 0.7 V vs. SCE (t2 = 0.03 s). Spectroscopic XPS investigations and SEM analysis were used in order to characterize the surface and morphology of the studied modified electrode. Cyclic voltammetry and chronoamperometry were used in order to evaluate the electrochemical/amperometric performance of the GC/MWCNT-Ni electrode toward the oxidation of some aliphatic alcohols in strong alkaline medium
Data-driven control of a Pendulum Wave Energy Converter: A Gaussian Process Regression approach
Get PDFThe energy coming from the motion of the waves of seas and oceans could be an important component in the solution of the energy problem related to the pursuit of alternatives to fossil fuels. However, wave energy is still technologically immature and it has not reached the economic feasibility required for economy of scale. One of the major technological challenges for the achievement of this goal is the development of control strategies capable of maximizing the extracted energy, adapting to the conditions of the seas and oceans that surround the Wave Energy Converter (WEC) devices. To perform this task, control systems often adopt explicitly control-oriented models, that are by nature affected by uncertainties. On the contrary, to address the problem a data-driven solution is proposed here. The presented strategy applies an optimization approach based on a Gaussian Process Regression (GPR) metamodel to learn the control strategy to be applied. In order to accelerate the learning process, we present a novel method that exploits in the initial phase a previous knowledge given by simulations with the system model and based on the co-kriging concept. To test this approach the Pendulum Wave Energy Converter has been adopted as a case study. To differentiate the previous knowledge and the real system behaviour, a simplified linear model is used to obtain the prior knowledge, while a complex nonlinear one acts as the environment in which simulate the behaviour of the real system. A month-long simulation is used to validate the effectiveness of the proposed strategy, showing the ability of adapting to a real system different from the simplified model on the basis only of data, and overcoming the model-based strategy in terms of performance
Joint Discount and Replenishment Parametric Policies for Perishable Products
Get PDFWe consider a joint discount and replenishment problem in a discrete periodic review fashion for the sale of a perishable product, characterized by limited deterministic shelf life, replenishment lead times, and stochastic demand. Customers decide what to buy according to a linear discrete choice model, balancing price and perceived quality, uniquely determined by the residual shelf life. The decisions we consider are: How many new items to order, the age of the items to be discounted, and how much discount to offer. In this context, we compare a set of policies mixing the constant order policy and the base stock one with some easy discounting policies, optimizing their parameters using a simulation-based optimization framework. To evaluate their performance in terms of revenue and quantity of scraped items, we consider four realistic instances for a grocery retailer characterized by products of different shelf life and variance of demand. Experiments show that best results are achieved by a base stock policy that discounts products of different ages based on a threshold: If the quantity of the inventory of a given age is greater than a threshold it applies a discount, otherwise no discount is proposed. In the presented configurations, this policy increases the average reward compared to policies that do not discoun
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
