{"id":1070,"date":"2016-06-27T16:53:06","date_gmt":"2016-06-27T16:53:06","guid":{"rendered":"http:\/\/kourentzes.com\/forecasting\/?p=1070"},"modified":"2016-10-15T10:06:26","modified_gmt":"2016-10-15T10:06:26","slug":"international-symposium-on-forecasting-presentations","status":"publish","type":"post","link":"https:\/\/kourentzes.com\/forecasting\/2016\/06\/27\/international-symposium-on-forecasting-presentations\/","title":{"rendered":"International Symposium on Forecasting Presentations"},"content":{"rendered":"<p>Last week I attended the <a href=\"https:\/\/forecasters.org\/isf\/\">International Symposium on Forecasting<\/a> 2016. It was very interesting and enjoyable. Apart from the workshop on <a href=\"http:\/\/kourentzes.com\/forecasting\/2016\/06\/19\/material-for-forecasting-with-r-a-practical-workshop\/\">forecasting with R<\/a>, I gave the following presentations:<\/p>\n<p><strong>Forecasting with Temporal Hierarchies<\/strong><br \/>\nThis presentation was given to the practitioner track of the conference and its aim was to introduce the basic idea of temporal hierarchies for forecasting and highlight the forecasting and business challenges they can help address. You can read more details in the <style type=\"text\/css\">#AnythingPopup_BoxContainer1\t{width:640px;height:480px;max-width:80%;background:#FFFFFF;border:1px solid #4D4D4D;padding:0;position:fixed;z-index:99999;cursor:default;-moz-border-radius: 10px;-webkit-border-radius: 10px;-khtml-border-radius: 10px;border-radius: 10px;   display:none;} #AnythingPopup_BoxContainerHeader1 {height:30px;background:#FFFFFF;border-top-right-radius:10px;-moz-border-radius-topright:10px;-webkit-border-top-right-radius:10px;-khtml-border-top-right-radius: 10px;border-top-left-radius:10px;-moz-border-radius-topleft:10px;-webkit-border-top-left-radius:10px;-khtml-border-top-left-radius: 10px;} #AnythingPopup_BoxContainerHeader1 a {color:#000000;font-family:Verdana,Arial;font-size:10pt;font-weight:bold;} #AnythingPopup_BoxTitle1 {float:left; margin:5px;color:#000000;font-family:Verdana,Arial;font-size:12pt;font-weight:bold;} #AnythingPopup_BoxClose1 {float:right;width:50px;margin:5px;} #AnythingPopup_BoxContainerBody1 {margin:10px;overflow:auto;height:420px;} #AnythingPopup_BoxContainerFooter1 {position: fixed;top:0;left:0;bottom:0;right:0;opacity: .3;-moz-opacity: .3;filter: alpha(opacity=30);z-index:999;display:none;} <\/style><a href='javascript:AnythingPopup_OpenForm(\"AnythingPopup_BoxContainer1\",\"AnythingPopup_BoxContainerBody1\",\"AnythingPopup_BoxContainerFooter1\",\"640\",\"480\");'>abstract<\/a><div style=\"display: none;\" id=\"AnythingPopup_BoxContainer1\"><div id=\"AnythingPopup_BoxContainerHeader1\"><div id=\"AnythingPopup_BoxTitle1\">Abstract<\/div><div id=\"AnythingPopup_BoxClose1\"><a href=\"javascript:AnythingPopup_HideForm('AnythingPopup_BoxContainer1','AnythingPopup_BoxContainerFooter1');\">Close<\/a><\/div><\/div><div id=\"AnythingPopup_BoxContainerBody1\">In forecasting we typically build our models and forecasts in the same frequency that our time series were collected (for example monthly or weekly). However, this is not always aligned with the decision making needs of organisations that may require even shorter term operational forecasts or longer term strategic forecasts at a quarterly or annual level. Furthermore, different planning needs and horizons should be aligned. Operational, tactical and strategic forecasts should be in agreement to avoid conflicting decision making. For example operational inventory decisions should be supported by mid-term production and procurement ones. Current forecast practice does not guarantee that, where independent predictions are produced at each level using various methods or human judgement. These may agree or not. A last point to consider in current forecasting practice is that from a modelling point of view, constructing forecasts using raw data at the original frequency that was collected may not be ideal from a statistical standpoint. Working at an aggregate or disaggregate level may help forecasting by revealing or filtering elements of the time series.\r<br \/>\r<br \/>Temporal hierarchies, a new development in time series modelling aims to address all the issues above. The principal idea is to model time series at multiple levels of temporal aggregation (for example: weekly, monthly, quarterly and annually) and combine the resulting predictions. There is a two-fold motivation for this. First, resulting forecasts are able to extract better the information captured in time series, as temporal aggregation allows attenuating or strengthening different components of the time series. Second, by modelling time series in this way we can ensure that short-term forecast (constructed at disaggregate levels, e.g. weekly) and long-term forecasts (constructed at aggregate levels, e.g. yearly) are aligned and can support decision making at all different levels. This provides a statistically sound way to achieve the so called `one-number\u2019 forecast. This presentation will introduce temporal hierarchies, show how to build and use them and demonstrate their advantages with real case studies.<\/div><\/div><div style=\"display: none;\" id=\"AnythingPopup_BoxContainerFooter1\"><\/div><br \/>\nDownload <a href=\"http:\/\/kourentzes.com\/forecasting\/wp-content\/uploads\/2016\/06\/ISF_Kourentzes_Temporal.pdf\">presentation<\/a>.<\/p>\n<p><strong>Measuring Forecasting Performance: A Complex Task<\/strong><br \/>\nThis research presentation introduces a new error metric to evaluate forecast performance. Although there has been substantial research on accuracy metrics, there has been very limited work on bias metrics that is an equally important dimension of performance. An interesting aspect of the proposed metric are the informative visualisations of accuracy and bias. You can read more details in the <style type=\"text\/css\">#AnythingPopup_BoxContainer2\t{width:640px;height:480px;max-width:80%;background:#FFFFFF;border:1px solid #4D4D4D;padding:0;position:fixed;z-index:99999;cursor:default;-moz-border-radius: 10px;-webkit-border-radius: 10px;-khtml-border-radius: 10px;border-radius: 10px;   display:none;} #AnythingPopup_BoxContainerHeader2 {height:30px;background:#FFFFFF;border-top-right-radius:10px;-moz-border-radius-topright:10px;-webkit-border-top-right-radius:10px;-khtml-border-top-right-radius: 10px;border-top-left-radius:10px;-moz-border-radius-topleft:10px;-webkit-border-top-left-radius:10px;-khtml-border-top-left-radius: 10px;} #AnythingPopup_BoxContainerHeader2 a {color:#000000;font-family:Verdana,Arial;font-size:10pt;font-weight:bold;} #AnythingPopup_BoxTitle2 {float:left; margin:5px;color:#000000;font-family:Verdana,Arial;font-size:12pt;font-weight:bold;} #AnythingPopup_BoxClose2 {float:right;width:50px;margin:5px;} #AnythingPopup_BoxContainerBody2 {margin:10px;overflow:auto;height:420px;} #AnythingPopup_BoxContainerFooter2 {position: fixed;top:0;left:0;bottom:0;right:0;opacity: .3;-moz-opacity: .3;filter: alpha(opacity=30);z-index:999;display:none;} <\/style><a href='javascript:AnythingPopup_OpenForm(\"AnythingPopup_BoxContainer2\",\"AnythingPopup_BoxContainerBody2\",\"AnythingPopup_BoxContainerFooter2\",\"640\",\"480\");'>abstract<\/a><div style=\"display: none;\" id=\"AnythingPopup_BoxContainer2\"><div id=\"AnythingPopup_BoxContainerHeader2\"><div id=\"AnythingPopup_BoxTitle2\">Abstract<\/div><div id=\"AnythingPopup_BoxClose2\"><a href=\"javascript:AnythingPopup_HideForm('AnythingPopup_BoxContainer2','AnythingPopup_BoxContainerFooter2');\">Close<\/a><\/div><\/div><div id=\"AnythingPopup_BoxContainerBody2\">Forecasting plays a crucial role in decision making and accurate forecasts can bring important benefits for organisations. Predictive performance is often separated into accuracy and bias, for which different metrics have been developed and used to varying degrees in research and practice. Exploring the literature one can conclude that forecast accuracy metrics have received more attention than bias metrics, even though the latter are very important for practice. One can also observe that the choice of metric can change the findings of an analysis. For example, this has been very pronounced in the judgemental forecasting literature, which we will use as a case study in our investigation. Typically judgemental forecasts and adjustments can enhance accuracy under certain circumstances, although they are biased given the nature of human behaviour. Researchers have been actively looking into possible causes and remedies of human bias; however we argue that their investigation has been hindered by the lack of adequate metrics. Motivated by this we develop a novel metric that overcomes the aforementioned limitations by using an innovative application of complex numbers theory. The new metric is successfully applied to analyse the judgemental forecasts of a household products manufacturer. We proceed to explore the properties of the metric and its general use in assessing the performance of forecasts.<\/div><\/div><div style=\"display: none;\" id=\"AnythingPopup_BoxContainerFooter2\"><\/div><br \/>\nDownload <a href=\"http:\/\/kourentzes.com\/forecasting\/wp-content\/uploads\/2016\/06\/ISF_Kourentzes_MRE.pdf\">presentation<\/a>.<\/p>\n<div class=\"SPOSTARBUST-Related-Posts\"><H3>Related Posts<\/H3><ul class=\"entry-meta\"><li class=\"SPOSTARBUST-Related-Post\"><a title=\"Stochastic Coherency in Forecast Reconciliation\" href=\"https:\/\/kourentzes.com\/forecasting\/2021\/07\/09\/stochastic-coherency-in-forecast-reconciliation\/\" rel=\"bookmark\">Stochastic Coherency in Forecast Reconciliation<\/a><\/li>\n<li class=\"SPOSTARBUST-Related-Post\"><a title=\"Visitor Arrivals Forecasts amid COVID-19: A Perspective from the Africa Team\" href=\"https:\/\/kourentzes.com\/forecasting\/2021\/07\/09\/visitor-arrivals-forecasts-amid-covid-19-a-perspective-from-the-africa-team\/\" rel=\"bookmark\">Visitor Arrivals Forecasts amid COVID-19: A Perspective from the Africa Team<\/a><\/li>\n<li class=\"SPOSTARBUST-Related-Post\"><a title=\"ISF 2020: A geometry inspired hierarchical forecasting methodology\" href=\"https:\/\/kourentzes.com\/forecasting\/2020\/10\/25\/isf-2020-using-information-from-the-business-environment-to-improve-forecasting\/\" rel=\"bookmark\">ISF 2020: A geometry inspired hierarchical forecasting methodology<\/a><\/li>\n<\/ul><\/div><!-- AddThis Advanced Settings generic via filter on the_content --><!-- AddThis Share Buttons generic via filter on the_content -->","protected":false},"excerpt":{"rendered":"<p>Last week I attended the International Symposium on Forecasting 2016. It was very interesting and enjoyable. Apart from the workshop on forecasting with R, I gave the following presentations: Forecasting with Temporal Hierarchies This presentation was given to the practitioner track of the conference and its aim was to introduce the basic idea of temporal\u2026 <span class=\"read-more\"><a href=\"https:\/\/kourentzes.com\/forecasting\/2016\/06\/27\/international-symposium-on-forecasting-presentations\/\">Read More &raquo;<\/a><\/span><!-- AddThis Advanced Settings generic via filter on get_the_excerpt --><!-- AddThis Share Buttons generic via filter on get_the_excerpt --><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[41,7],"tags":[62,61,24,60,38,36,68],"_links":{"self":[{"href":"https:\/\/kourentzes.com\/forecasting\/wp-json\/wp\/v2\/posts\/1070"}],"collection":[{"href":"https:\/\/kourentzes.com\/forecasting\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/kourentzes.com\/forecasting\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/kourentzes.com\/forecasting\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/kourentzes.com\/forecasting\/wp-json\/wp\/v2\/comments?post=1070"}],"version-history":[{"count":0,"href":"https:\/\/kourentzes.com\/forecasting\/wp-json\/wp\/v2\/posts\/1070\/revisions"}],"wp:attachment":[{"href":"https:\/\/kourentzes.com\/forecasting\/wp-json\/wp\/v2\/media?parent=1070"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/kourentzes.com\/forecasting\/wp-json\/wp\/v2\/categories?post=1070"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/kourentzes.com\/forecasting\/wp-json\/wp\/v2\/tags?post=1070"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}<!-- WP Super Cache is installed but broken. The constant WPCACHEHOME must be set in the file wp-config.php and point at the WP Super Cache plugin directory. -->