Forecasts Of Future Demand Research Articles

Measuring performance

Most organizations today have a set of key performance indicators (KPIs) that are used for decision-making. Because a balanced scorecard approach has been widely adopted, typically KPIs have moved beyond the basic financial metrics. However, developing the right set of KPIs is an important step in promoting continuous improvement and overall business success. Organization that implement six sigma or lean six sigma have a built-in set of KPIs, such as defects, ppm defective, process yields, process cycle times, and a variety of inventory statistics, such as WIP inventory. But I don't think this goes far enough in most situations. KPIs should be traceable to customer satisfaction, both for external customers and internal ones. Organizations should formalize customer requirements and then evaluate how they are doing with respect to this list when they conduct strategic planning sessions. This is a good way to develop the right KPIs. However, overemphasis on short-term financial results can skew this process. Too much focus on quarterly growth in sales or revenue and deflect attention from the issues that contribute to long-term business growth and success. Organizations often gravitate towards collecting data that is easy to obtain, but may not be necessarily useful. An example is information about customer satisfaction data. Surveys can be useful, but may not tell the complete story. One organization that I am familiar with has a customer service line. They reported very few serious complaints from that source. Analysis revealed that the average waiting time for customers that used this line was in excess of 30 minutes. Furthermore, the ability of the system to place calls on hold was limited, so a significant number of calls were “blocked”; that is, they were not answered at all. So the volume of customer issues that this service was designed to serve was dramatically underestimated. Some KPIs are lagging indicators of business performance. Examples include sales volumes and maintenance expenses. These are usually easy to generate, but may not provide much indication of future success. Reliable forecasts of future demand (demand isn't necessarily the same as sales) is usually a better business indicator. Leading indicators are harder to devise, almost always depend on the specific nature of the individual organization, and may be difficult to generate. For example, cycle time for new product introduction is often a critical measure of future business success in many industries. If this KPI is unsatisfactory or is getting longer for unexplained reasons it may indicate an area for lean six sigma intervention. Performance measurement is an important management tool for evaluating and improving organizational success. Leading KPIs can be an effective “canary in the coal mine” warning of impending trouble. The investment required to develop and maintain the correct set of KPIs will pay many dividends.

Forecasting big time series

Time series forecasting is a key ingredient in the automation and optimization of business processes: in retail, deciding which products to order and where to store them depends on the forecasts of future demand in different regions; in cloud computing, the estimated future usage of services and infrastructure components guides capacity planning; and workforce scheduling in warehouses, call centers, factories requires forecasts of the future workload. Recent years have witnessed a paradigm shift in forecasting techniques and applications, from computer-assisted model- and assumption-based to data-driven and fully-automated. This shift can be attributed to the availability of large, rich, and diverse time series data sources, posing unprecedented challenges to traditional time series forecasting methods. As such, how can we build statistical models to efficiently and effectively learn to forecast from large and diverse data sources? How can we leverage the statistical power of "similar" time series to improve forecasts in the case of limited observations? What are the implications for building forecasting systems that can handle large data volumes? The objective of this tutorial is to provide a concise and intuitive overview of the most important methods and tools available for solving large-scale forecasting problems. We review the state of the art in three related fields: (1) classical modeling of time series, (2) scalable tensor methods, and (3) deep learning for forecasting. Further, we share lessons learned from building scalable forecasting systems. While our focus is on providing an intuitive overview of the methods and practical issues, we also present technical details underlying these powerful tools.

Review of asset management for metro systems: challenges and opportunities

ABSTRACTMetro systems play a crucial role in the movement of millions of passengers worldwide as commuters rely on a fast, reliable, and convenient underground railway for their daily transportation. However, in many cases, the quality of the service that can be delivered, including performance, attractiveness, and customer satisfaction, are constrained by poorly maintained infrastructure. Meanwhile, effective planning to maintain, rehabilitate, replace and expand existing systems must respect technical, social, political, financial, and management constraints. There is a lack of a comprehensive framework for managing metro assets. This is mainly due to the multiplicity of components; the complexity of their interdependencies; common lack of historical data and performance indicators; and unavailability of a unified framework that integrates forecasts of future demand with decision-making systems. The main objective of this research is to review available studies and models for underground rail systems, identify the main strategic-operational planning gaps, and propose critical tasks for a comprehensive asset management framework. The platform developed in this research is suitable for further studies in urban railways such as Rail Rapid Transit (underground and surface), Light Rail Transit, and suburban trains as well as other modes of transport (e.g. traditional buses, Bus-Rapid-Transit).

Supply and Demand Analysis, Future Demand Forecast, and Countermeasure Studies for Forage Materials in China

Supply and Demand Analysis, Future Demand Forecast, and Countermeasure Studies for Forage Materials in China

Assessing the impact of solar PV on domestic electricity consumption: Exploring the prospect of rebound effects

This study examines patterns of electricity use by households in Sydney who have installed solar photovoltaic (PV) technology compared to those who have not in order to assess the impact of government solar incentive schemes, and to identify whether conservation or rebound (increased consumption) effects are associated with rooftop PV. Findings have significance in determining whether a rebound effect needs to be factored into projected energy/carbon savings from solar PV installation. At issue is the robustness of carbon mitigation estimates included in future rounds of international climate change agreements as well as local forecasts of future electricity demand affecting the national grid. Analysis and modelling was undertaken on billing data for the period 2007–2014 on a representative sample of 4819 households. The sample comprised three groups: households who were early adopters and installed PV under a 60c/kWh gross feed-in tariff scheme, a group who installed under a 20c/KWh gross feed-in scheme and a control group with no PV. Econometric modelling undertaken on energy consumption behaviour of households with versus without local renewable energy generation revealed that on a kWh basis, the rebound effect is estimated to erode up to one fifth of the carbon benefit of renewable energy generated by solar PV.

Railway capacity and expansion analysis using time discretized paths

When making investments in railway infrastructure it is important to be able to identify the limits for freight transportation in order to not only use the infrastructure in the best possible way, but to also guide future capacity investments. This paper presents a model to assess the capacity of railway freight transportation on a long term strategic level. The model uses an hourly time discretization and analyses the impact of railway network expansions based on future demand forecasts. It provides an optimal macroscopic freight train schedule and can indicate the time and place of any congestion. In addition, two expansions of the primary model are developed. The first can be used to determine the minimal number of expansions needed to ensure all freight can be feasibly routed, while the second can be used to schedule freight trains at hours not congested by passenger trains using variable penalties for the different passenger busy time slots. As part of a European Union project, all models are applied to a realistic case study that focuses on analyzing the capacity of railway network, in Denmark and Southern Sweden using demand forecasts for 2030. Results suggest that informative solutions can be found quickly with the proposed approach.

Open-source Software for Demand Forecasting of Clinical Laboratory Test Volumes Using Time-series Analysis

Background: Demand forecasting is the area of predictive analytics devoted to predicting future volumes of services or consumables. Fair understanding and estimation of how demand will vary facilitates the optimal utilization of resources. In a medical laboratory, accurate forecasting of future demand, that is, test volumes, can increase efficiency and facilitate long-term laboratory planning. Importantly, in an era of utilization management initiatives, accurately predicted volumes compared to the realized test volumes can form a precise way to evaluate utilization management initiatives. Laboratory test volumes are often highly amenable to forecasting by time-series models; however, the statistical software needed to do this is generally either expensive or highly technical. Method: In this paper, we describe an open-source web-based software tool for time-series forecasting and explain how to use it as a demand forecasting tool in clinical laboratories to estimate test volumes. Results: This tool has three different models, that is, Holt-Winters multiplicative, Holt-Winters additive, and simple linear regression. Moreover, these models are ranked and the best one is highlighted. Conclusion: This tool will allow anyone with historic test volume data to model future demand.

Modeling and Forecasting Electricity Demand in Azerbaijan Using Cointegration Techniques

Policymakers in developing and transitional economies require sound models to: (i) understand the drivers of rapidly growing energy consumption and (ii) produce forecasts of future energy demand. This paper attempts to model electricity demand in Azerbaijan and provide future forecast scenarios—as far as we are aware this is the first such attempt for Azerbaijan using a comprehensive modelling framework. Electricity consumption increased and decreased considerably in Azerbaijan from 1995 to 2013 (the period used for the empirical analysis)—it increased on average by about 4% per annum from 1995 to 2006 but decreased by about 4½% per annum from 2006 to 2010 and increased thereafter. It is therefore vital that Azerbaijani planners and policymakers understand what drives electricity demand and be able to forecast how it will grow in order to plan for future power production. However, modeling electricity demand for such a country has many challenges. Azerbaijan is rich in energy resources, consequently GDP is heavily influenced by oil prices; hence, real non-oil GDP is employed as the activity driver in this research (unlike almost all previous aggregate energy demand studies). Moreover, electricity prices are administered rather than market driven. Therefore, different cointegration and error correction techniques are employed to estimate a number of per capita electricity demand models for Azerbaijan, which are used to produce forecast scenarios for up to 2025. The resulting estimated models (in terms of coefficients, etc.) and forecasts of electricity demand for Azerbaijan in 2025 prove to be very similar; with the Business as Usual forecast ranging from about of 19½ to 21 TWh.

A Research on Supply Chain Network of RMG Sector

Readymade Garment (RMG) industry is one of the strongest sectors supporting the economy of Bangladesh and proper business strategies need to be applied to maintain its growth. One way to decrease the supply time is layout improvement and a better forecasting method. Here, different forecasting methods, comparison between them and improvement of plant layout are mainly focused using data collected from several factories. To determine the future demand (forecasting) of a certain company different methods (exponential smoothing, weighted moving average etc.) are used. By analyzing and comparing; a better method is proposed to predict more accurate future demand. Production efficiency and Achieved target are also found from collected data. In this research, an improved layout is proposed to a company; where line balancing is better and lead time is minimized making the supply chain more efficient. With all these analysis and data collection, a better and improved supply chain network can be used in Bangladeshi RMG sector.

Learning in Advance Selling with Heterogeneous Consumers

The advance selling strategy is implemented when a firm offers consumers the opportunity to order its product in advance of the regular selling season. Advance selling reduces uncertainty for both the firm and the buyer and enables the firm to update its forecast of future demand. The distinctive feature of the present study of advance selling is that we divide consumers into two groups, experienced and inexperienced. Experienced consumers know their valuations of the product in advance. The presence of experienced consumers yields new insights. Specifically, pre-orders from experienced consumers lead to a more precise forecast of future demand by the firm. We show that the firm will always adopt advance selling and that the optimal pre-order price may be at a discount or a premium relative to the regular selling price.

Distributions of forecasting errors of forecast combinations: Implications for inventory management

Inventory control systems rely on accurate and robust forecasts of future demand to support decisions such as setting of safety stocks. The combination of multiple forecasts is shown to be effective not only in reducing forecast errors, but also in being less sensitive to limitations of a single model. Research on forecast combination has primarily focused on improving accuracy, largely ignoring the overall shape and distribution of forecast errors. Nonetheless, these are essential for managing the level of aversion to risk and uncertainty for companies. This study examines the forecast error distributions of base and combination forecasts and their implications for inventory performance. It explores whether forecast combinations transform the forecast error distribution towards desired properties for safety stock calculations, typically based on the assumption of normally distributed errors and unbiased forecasts. In addition, it considers the similarity between in- and out-of-sample characteristics of such errors and the impact of different lead times. The effects of established combination methods are explored empirically using a representative set of forecasting methods and a dataset of 229 weekly demand series from a leading household and personal care UK manufacturer. Findings suggest that forecast combinations make the in- and out-of-sample behaviour more consistent, requiring less safety stock on average than base forecasts. Furthermore we find that using in-sample empirical error distributions of combined forecasts approximates well the out-of-sample ones, in contrast to base forecasts.

Short-term Forecasting of Intermodal Freight Using ANNs and SVR: Case of the Port of Algeciras Bay

Forecasting of future intermodal traffic demand is very important for decision making in ports operations management. The use of accurate prediction tools is an issue that awakens a lot of interest among transport researchers. Intermodal freight forecasting plays an important role in ports management and in the planning of the principal port activities. Hence, the study is carried out under the motivation of knowing that modeling the freight transport flows could facilitate the management of the infrastructure and optimize the resources of the ports facilities. The use of advanced models for freight forecasting is essential to improve the port level-service and competitiveness. In this paper, two forecasting-models are presented and compared to predict the freight volume. The models developed and tested are based on Artificial Neural Networks and Support Vector Machines. Both techniques are based in a historical data and these methods forecast the daily weight of the freight with one week in advance. The performance of the models is evaluated on real data from Ro-Ro freight transport in the Port of Algeciras Bay. This work proposes and compares different approaches to determine the best prediction. In order to select the best model a multicomparison procedure is developed using several statistical test. The results of the assessed models show a promising tool to predict Ro-Ro transport flows with accuracy.

Future Arable Land Requirement of Pig Production in China

<strong><strong> </strong></strong><p>China’s pig industry is experiencing a dramatic increase to meet increasing consumption demand. How these changes influence the limited arable land resources through consuming grain as feed has not been clearly understood. In this manuscript, we calculate the arable land requirement for pig industry (LRP) from 2001 to 2013 and forecast future demand towards 2050 from the point of production, in order to quantify the pressure in different scenarios. The results indicate that the LRP has increased from 22.0 Million Ha in 2001 to 31.6 Million Ha in 2013. LRP will be 23.7-29.4 Million Ha in 2030 and 11.6-18.7 Million Ha in 2050 according to different scenarios. Logarithmic Mean Divisia Index (LMDI) decomposition method is assessed to the effect of population, consumption and technology for three time periods e.g. 2010-2030; 2030-2050 and 2010-2050. And technology will become primary reason. These findings could help optimizing the relationships between limited arable land resources and development of pig industry, and promote sustainable development of the pig industry.</p><strong></strong>

Slot auction in an airport network with demand uncertainty

This paper investigates the effectiveness of airport slot auction by developing a two-stage model, which distributes slots among competing airlines using an ascending-bid multi-unit auction. Airlines assign different values to slots at peak and off-peak periods, and each carrier has its private (subjective) forecast of future demand. Conditional on the slots available to them, airlines compete in frequency, fare, and aircraft size over a congested airport network. The market outcome under such a scheme is benchmarked to those under an ex ante allocation and an ex post allocation by a social planner. Comparison results suggest that the auction-based scheme is inferior to the other two schemes when there is little fluctuation in demand, whereas the auction-based system is more effective when there is substantial demand uncertainty. Auctioning some grandfathered slots can improve social welfare but the marginal effect may diminish quickly.

Real-time Burst Detection in Water Distribution Systems Using a Bayesian Demand Forecasting Methodology

The negative consequences of non-revenue water losses from Water Distribution Systems (WDS) can be reduced through the successful and prompt identification of bursts and abnormal conditions. Here we present a preliminary investigation into the application of a probabilistic demand forecasting approach to identify pipe bursts. The method produces a probabilistic forecast of future demand under normal conditions. This, in turn, quantifies the probability that a future observation is abnormal. The method, when tested using synthetic bursts applied to a demand time-series for a UK WDS, performed well in detecting bursts, particularly those >5% of mean daily flow at night time.

The generators of paratransit trips by persons with disabilities

Identifying the generators of paratransit trips by persons with disabilities is important to comprehend the current demand patterns and forecast future demand. Only a handful of studies have been conducted so far to identify the generators of paratransit trips and most focused on the home end of the trips. Given some of the inconsistencies in past studies and the scarcity of studies on the generators of trips away from home, this study attempts to identify the generators of paratransit trips beginning and ending at clients’ homes and away from home. It uses an extremely large dataset consisting of 1.91 million trips made by NJ TRANSIT’s Access Link clients, socioeconomic data from the American Community Survey, employment data from the Longitudinal Employer-Household Dynamics, and establishment data from Dun and Bradstreet. The analytical methods include an ordinary least squares model (OLS) and several spatial generalized linear mixed models (GLMM) to identify the characteristics of census block groups associated with Access Link trip generation at home and away from home, Geographic Information System (GIS) analysis to identify the types of establishments located in the immediate vicinity of drop-offs, and a multinomial logit model (MNL) to examine the relationship between the characteristics of the establishments in the vicinity of drop-offs and the characteristics of the dropped-off clients. Together, the various analyses provide useful insights about paratransit trip generators at the macro and micro levels. Some implications of the findings are discussed.

Modeling Traffic Demand of Tourist Areas Based on a Joint Prediction Model

Tourist traffic plays a crucial role in the development of tourist attractions. A complete transportation system is a prerequisite to support and guarantee the implementation of all tourist functions. In the special planning of tourist area, predicting and analyzing tourist traffic demand lays the important foundation for other content. Due to the lack of historical data in the newly-developed tourist areas, selection of scenic transportation modes, determination of the size of transportation facilities and traffic management methods should be made on the basis of accurate forecast of future traffic demand. Considering the characteristics of the newly-developed tourist area, this article proposed a tourist traffic prediction model based on the gray model and the environmental capacity limited model. With the example of the tourist area of Nishan, Qufu, this paper predicted the total annual tourist reception capacity as well as tourist numbers by the prediction model. The model results show that the joint prediction model have positive significance in improving reasonableness and accuracy of predicting tourist traffic demand.

Airport Curbside and Parking Area Operations at BIA – Analysis of User Behavior

Airport curbside, where travelers and their baggage enter and exit the terminal, and the designated parking area are important components in airport land-side facilities. Passengers expect safe and efficient roadway operations even as volumes increase, but the design and capacity of .the curbside are often constrained by the terminal building and the proximity of on-airport land-side infrastructure. The operating characteristics of airport terminal curbside differ significantly from those of most other roadways due to several reasons such as vehicle dwell time, maneuver vehicles to and from adjacent lane, variation in demand etc. The capacity of a curbside roadway is defined both by the number of vehicles that can be accommodated while stopping to pick up or drop off passengers and the number that can be accommodated while traveling past the curbside in the through lanes. Therefore a study of operations at curbside and parking area is important to identify issues related to existing and future demand levels. The main focus of the paper is on the evaluation of vehicle operations and passenger behavior at the BIA terminal access roadway, weaving segment, arrival and departure curbside roadways and terminal car park. Analysis of vehicular traffic, travel mode choices, and curbside roadway vehicle queues, vehicle dwelling times, passenger occupancy time at curbs and passenger processing and walking times will provide useful information for developing plans for operational improvements as well as for future expansions. Using the available data, the demand and the capacity at these facilities are evaluated to estimate the existing level of service. In addition, measures were identified to improve the operational efficiency of these facilities and design improvements are proposed to ensure good operational efficiency for the forecast future demand. ENGINEER, Vol. 47, No. 04, pp. 43-51, 2014

The Application of Trend Analysis for Coal Demand Modeling

In the current modeling, trend analysis is used to model coal consumption (CC) and forecast the future coal demand. For modeling, trends in the CC of the world and the major coal consuming countries during 1965–2010 are identified. According to the trend observed, the appropriate regression analysis is employed to catch the best model concerning the relations between the CC and the years. The developed models are tested by t-distribution, F-distribution and residual analysis. Statistically significant trends are determined for the United States, India, Japan, South Africa, South Korea, Australia, Taiwan, Turkey, Thailand, and the world. The results show that the proposed models can be used for the forecasting of future coal demand. It is also concluded that differences between forecasted CC by proposed models and forecasted CC by British Petroleum and International Energy Agency are also in the acceptable range.

Evaluation of a Strategic Road Pricing Scheme Accounting for Day-to-Day and Long-Term Demand Uncertainty

Transport network pricing schemes are an integral traffic management strategy that can be implemented to reduce congestion, among other network impacts. However, the problem of determining tolls becomes much more complex when multiple sources of demand uncertainty are considered. This paper proposes a novel tolling model based on a particular variant of strategic user equilibrium in which users base their route choice decisions on a known demand distribution. The study showed that by using an average daily demand, a marginal social cost–based tolling approach could induce near optimal conditions in a strategic network. However, uncertainty was associated with the long-term future planning demand; inaccurate forecasts of future demand could result in poor realized tolling scheme performance. Therefore, this paper also proposes a method to test the robustness of a tolling scheme, which is the reliability of the link tolls under a range of future demand scenario realizations. Results demonstrated that evaluations of strategic tolling schemes differed when both the short-term and the long-term uncertainty in demand were accounted for, and furthermore suggested that future research into the integration of multiple sources of uncertainty into the pricing scheme evaluation is merited.