Search results for "Forecast"
showing 10 items of 417 documents
Approaching sales forecasting using recurrent neural networks and transformers
2022
Accurate and fast demand forecast is one of the hot topics in supply chain for enabling the precise execution of the corresponding downstream processes (inbound and outbound planning, inventory placement, network planning, etc). We develop three alternatives to tackle the problem of forecasting the customer sales at day/store/item level using deep learning techniques and the Corporaci\'on Favorita data set, published as part of a Kaggle competition. Our empirical results show how good performance can be achieved by using a simple sequence to sequence architecture with minimal data preprocessing effort. Additionally, we describe a training trick for making the model more time independent and…
Forecasting : theory and practice
2022
Forecasting has always been at the forefront of decision making and planning. The uncertainty that surrounds the future is both exciting and challenging, with individuals and organisations seeking to minimise risks and maximise utilities. The large number of forecasting applications calls for a diverse set of forecasting methods to tackle real-life challenges. This article provides a non-systematic review of the theory and the practice of forecasting. We provide an overview of a wide range of theoretical, state-of-the-art models, methods, principles, and approaches to prepare, produce, organise, and evaluate forecasts. We then demonstrate how such theoretical concepts are applied in a varie…
An ensemble approach to short-term forecast of COVID-19 intensive care occupancy in Italian Regions
2020
Abstract The availability of intensive care beds during the COVID‐19 epidemic is crucial to guarantee the best possible treatment to severely affected patients. In this work we show a simple strategy for short‐term prediction of COVID‐19 intensive care unit (ICU) beds, that has proved very effective during the Italian outbreak in February to May 2020. Our approach is based on an optimal ensemble of two simple methods: a generalized linear mixed regression model, which pools information over different areas, and an area‐specific nonstationary integer autoregressive methodology. Optimal weights are estimated using a leave‐last‐out rationale. The approach has been set up and validated during t…
KFAS : Exponential Family State Space Models in R
2017
State space modelling is an efficient and flexible method for statistical inference of a broad class of time series and other data. This paper describes an R package KFAS for state space modelling with the observations from an exponential family, namely Gaussian, Poisson, binomial, negative binomial and gamma distributions. After introducing the basic theory behind Gaussian and non-Gaussian state space models, an illustrative example of Poisson time series forecasting is provided. Finally, a comparison to alternative R packages suitable for non-Gaussian time series modelling is presented.
Domain-specific transfer learning in the automated scoring of tumor-stroma ratio from histopathological images of colorectal cancer
2023
Tumor-stroma ratio (TSR) is a prognostic factor for many types of solid tumors. In this study, we propose a method for automated estimation of TSR from histopathological images of colorectal cancer. The method is based on convolutional neural networks which were trained to classify colorectal cancer tissue in hematoxylin-eosin stained samples into three classes: stroma, tumor and other. The models were trained using a data set that consists of 1343 whole slide images. Three different training setups were applied with a transfer learning approach using domain-specific data i.e. an external colorectal cancer histopathological data set. The three most accurate models were chosen as a classifie…
Remote sensing and climate data as a key for understanding fasciolosis transmission in the Andes: review and update of an ongoing interdisciplinary p…
2006
Fasciolosis caused by Fasciola hepatica in various South American countries located on the slopes of the Andes has been recognized as an important public health problem. However, the importance of this zoonotic hepatic parasite was neglected until the last decade. Countries such as Peru and Bolivia are considered to be hyperendemic areas for human and animal fasciolosis, and other countries such as Chile, Ecuador, Colombia and Venezuela are also affected. At the beginning of the 1990s a multidisciplinary project was launched with the aim to shed light on the problems related to this parasitic disease in the Northern Bolivian Altiplano. A few years later, a geographic information system (GIS…
Impact of climate change and man-made irrigation systems on the transmission risk, long-term trend and seasonality of human and animal fascioliasis i…
2014
Large areas of the province of Punjab, Pakistan are endemic for fascioliasis, resulting in high economic losses due to livestock infection but also affecting humans directly. The prevalence in livestock varies pronouncedly in space and time (1-70%). Climatic factors influencing fascioliasis presence and potential spread were analysed based on data from five mete- orological stations during 1990-2010. Variables such as wet days (Mt), water-budget-based system (Wb-bs) indices and the normalized difference vegetation index (NDVI), were obtained and correlated with geographical distribution, seasonality patterns and the two-decade evolution of fascioliasis in livestock throughout the province. …
Corporate Investment, Debt and Liquidity Choices in the Light of Financial Constraints and Hedging Needs
2015
We examine firms' simultaneous choice of investment, debt financing and liquidity in a large sample of US corporates between 1980 and 2014. We partition the sample according to the firms' financial constraints and their needs to hedge against future shortfalls in operating income. In contrast to earlier work, our joint estimation approach shows that cash flows affect the corporate decisions of unconstrained firms more strongly than those of constrained firms. Investment-cash flow sensitivities are particularly intense for unconstrained firms with high hedging needs. Investment opportunities (as proxied by Q), however, play a larger role for constrained firms with the effects being strongest…
Financial constraints and cash–cash flow sensitivity
2014
This article explores the cash–cash flow relationship by comparing financially constrained and financially unconstrained companies. Unlike previous research, we test the sensitivity of cash to cash flow by considering unlisted firms as constrained and listed firms as unconstrained. Our empirical evidence is based on findings from Spanish firms and is consistent with the core rationale that unlisted firms face more difficulties than their listed counterparts when looking for funding from external markets. As a result, unlisted firms tend to hoard significant amounts of cash out of the generated cash flow, while listed firms do not. Our findings are robust to a number of additional empirical …
Wave Energy Assessment around the Aegadian Islands (Sicily)
2019
This paper presents the estimation of the wave energy potential around the Aegadian islands (Italy), carried out on the basis of high resolution wave hindcast. This reanalysis was developed employing Weather Research and Forecast (WRF) and WAVEWATCH III ® models for the modelling of the atmosphere and the waves, respectively. Wave climate has been determined using the above-mentioned 32-year dataset covering the years from 1979 to 2010. To improve the information about wave characteristics regarding spatial details, i.e., increasing wave model resolution, especially in the nearshore region around the islands, a SWAN (Simulating WAves Nearshore) wave propagation model was used. Results obtai…