Lawrence Snyder

Mohammad Pirhooshyaran, Lawrence V. Snyder

We propose a framework that uses deep neural networks (DNN) to optimize inventory decisions in complex multi-echelon supply chains. We first introduce pairwise modeling of general stochastic multi-echelon inventory optimization (SMEIO). Then, we present a framework which uses DNN agents to directly determine order-up-to levels between any adjacent pair of nodes in the supply chain. Our model considers a finite horizon and accounts for the initial inventory conditions. Our method is suitable for a wide variety of supply chain networks, including general topologies that may contain both assembly and distribution nodes, and systems with nonlinear cost structures. We first numerically demonstrate the effectiveness of the method by showing that its solutions are close to the optimal solutions for single-node and serial supply chain networks, for which exact methods are available. Then, we investigate more general supply chain networks and find that the proposed method performs better in terms of both objective function values and the number of interactions with the environment compared to alternate methods.

Ehsan Khodabandeh, Lawrence V. Snyder, John Dennis et al.

We consider a wide family of vehicle routing problem variants with many complex and practical constraints, known as rich vehicle routing problems, which are faced on a daily basis by C.H. Robinson (CHR). Since CHR has many customers, each with distinct requirements, various routing problems with different objectives and constraints should be solved. We propose a set partitioning framework with a number of route generation algorithms, which have shown to be effective in solving a variety of different problems. The proposed algorithms have outperformed the existing technologies at CHR on 10 benchmark instances and since, have been embedded into the company's transportation planning and execution technology platform.

Mohammad Pirhooshyaran, Katya Scheinberg, Lawrence V. Snyder

This study introduces a framework for the forecasting, reconstruction and feature engineering of multivariate processes along with its renewable energy applications. We integrate derivative-free optimization with an ensemble of sequence-to-sequence networks and design a new resampling technique called additive resampling, which, along with Bootstrap aggregating (bagging) resampling, are applied to initialize the ensemble structure. Moreover, we explore the proposed framework performance on three renewable energy sources---wind, solar and ocean wave---and conduct several short- to long-term forecasts showing the superiority of the proposed method compared to numerous machine learning techniques. The findings indicate that the introduced method performs more accurately when the forecasting horizon becomes longer. In addition, we modify the framework for automated feature selection. The model represents a clear interpretation of the selected features. Furthermore, we investigate the effects of different environmental and marine factors on the wind speed and ocean output power, respectively, and report the selected features. Finally, we explore the online forecasting setting and illustrate that the model outperforms alternatives through different measurement errors.

Mohammad Pirhooshyaran, Lawrence V. Snyder

This article explores the concepts of ocean wave multivariate multistep forecasting, reconstruction and feature selection. We introduce recurrent neural network frameworks, integrated with Bayesian hyperparameter optimization and Elastic Net methods. We consider both short- and long-term forecasts and reconstruction, for significant wave height and output power of the ocean waves. Sequence-to-sequence neural networks are being developed for the first time to reconstruct the missing characteristics of ocean waves based on information from nearby wave sensors. Our results indicate that the Adam and AMSGrad optimization algorithms are the most robust ones to optimize the sequence-to-sequence network. For the case of significant wave height reconstruction, we compare the proposed methods with alternatives on a well-studied dataset. We show the superiority of the proposed methods considering several error metrics. We design a new case study based on measurement stations along the east coast of the United States and investigate the feature selection concept. Comparisons substantiate the benefit of utilizing Elastic Net. Moreover, case study results indicate that when the number of features is considerable, having deeper structures improves the performance.

Mohammadreza Nazari, Majid Jahani, Lawrence V. Snyder et al.

Although reinforcement learning (RL) can provide reliable solutions in many settings, practitioners are often wary of the discrepancies between the RL solution and their status quo procedures. Therefore, they may be reluctant to adapt to the novel way of executing tasks proposed by RL. On the other hand, many real-world problems require relatively small adjustments from the status quo policies to achieve improved performance. Therefore, we propose a student-teacher RL mechanism in which the RL (the "student") learns to maximize its reward, subject to a constraint that bounds the difference between the RL policy and the "teacher" policy. The teacher can be another RL policy (e.g., trained under a slightly different setting), the status quo policy, or any other exogenous policy. We formulate this problem using a stochastic optimization model and solve it using a primal-dual policy gradient algorithm. We prove that the policy is asymptotically optimal. However, a naive implementation suffers from high variance and convergence to a stochastic optimal policy. With a few practical adjustments to address these issues, our numerical experiments confirm the effectiveness of our proposed method in multiple GridWorld scenarios.

Mohammadreza Nazari, Afshin Oroojlooy, Lawrence V. Snyder et al.

We present an end-to-end framework for solving the Vehicle Routing Problem (VRP) using reinforcement learning. In this approach, we train a single model that finds near-optimal solutions for problem instances sampled from a given distribution, only by observing the reward signals and following feasibility rules. Our model represents a parameterized stochastic policy, and by applying a policy gradient algorithm to optimize its parameters, the trained model produces the solution as a sequence of consecutive actions in real time, without the need to re-train for every new problem instance. On capacitated VRP, our approach outperforms classical heuristics and Google's OR-Tools on medium-sized instances in solution quality with comparable computation time (after training). We demonstrate how our approach can handle problems with split delivery and explore the effect of such deliveries on the solution quality. Our proposed framework can be applied to other variants of the VRP such as the stochastic VRP, and has the potential to be applied more generally to combinatorial optimization problems.

Afshin Oroojlooyjadid, Lawrence Snyder, Martin Takáč

In multi-echelon inventory systems the performance of a given node is affected by events that occur at many other nodes and in many other time periods. For example, a supply disruption upstream will have an effect on downstream, customer-facing nodes several periods later as the disruption "cascades" through the system. There is very little research on stock-out prediction in single-echelon systems and (to the best of our knowledge) none on multi-echelon systems. However, in real the world, it is clear that there is significant interest in techniques for this sort of stock-out prediction. Therefore, our research aims to fill this gap by using deep neural networks (DNN) to predict stock-outs in multi-echelon supply chains.

Afshin Oroojlooyjadid, MohammadReza Nazari, Lawrence Snyder et al.

The beer game is a widely used in-class game that is played in supply chain management classes to demonstrate the bullwhip effect. The game is a decentralized, multi-agent, cooperative problem that can be modeled as a serial supply chain network in which agents cooperatively attempt to minimize the total cost of the network even though each agent can only observe its own local information. Each agent chooses order quantities to replenish its stock. Under some conditions, a base-stock replenishment policy is known to be optimal. However, in a decentralized supply chain in which some agents (stages) may act irrationally (as they do in the beer game), there is no known optimal policy for an agent wishing to act optimally. We propose a machine learning algorithm, based on deep Q-networks, to optimize the replenishment decisions at a given stage. When playing alongside agents who follow a base-stock policy, our algorithm obtains near-optimal order quantities. It performs much better than a base-stock policy when the other agents use a more realistic model of human ordering behavior. Unlike most other algorithms in the literature, our algorithm does not have any limits on the beer game parameter values. Like any deep learning algorithm, training the algorithm can be computationally intensive, but this can be performed ahead of time; the algorithm executes in real time when the game is played. Moreover, we propose a transfer learning approach so that the training performed for one agent and one set of cost coefficients can be adapted quickly for other agents and costs. Our algorithm can be extended to other decentralized multi-agent cooperative games with partially observed information, which is a common type of situation in real-world supply chain problems.

Afshin Oroojlooyjadid, Lawrence Snyder, Martin Takáč

The newsvendor problem is one of the most basic and widely applied inventory models. There are numerous extensions of this problem. If the probability distribution of the demand is known, the problem can be solved analytically. However, approximating the probability distribution is not easy and is prone to error; therefore, the resulting solution to the newsvendor problem may be not optimal. To address this issue, we propose an algorithm based on deep learning that optimizes the order quantities for all products based on features of the demand data. Our algorithm integrates the forecasting and inventory-optimization steps, rather than solving them separately, as is typically done, and does not require knowledge of the probability distributions of the demand. Numerical experiments on real-world data suggest that our algorithm outperforms other approaches, including data-driven and machine learning approaches, especially for demands with high volatility. Finally, in order to show how this approach can be used for other inventory optimization problems, we provide an extension for (r,Q) policies.