The presentation, after a quick overview of the Belgian project, focuses the attention on how combining scanner data and data coming from classical price collection. Then the issues concerning the link to COICOP classification are discussed. Moreover, the treatment of relaunches and the use of internal codes are illustrated. In the last part of the presentation some figures are showed referred to the comparison between unit values and observed prices and to the comparison between the indices derived from scanner data and those ones derived from traditional data collection. A slide dedicated to the future developments of Belgian project completes the presentation.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
The Polish project on scanner data had its first step in 2011, when the cooperation with one retail chain was established. In May 2015, the agreement with the fourth retail trade chain (the most important one) was achieved and the share covered with scanner data increased to nearly 50% of the supermarket and hypermarket in terms of turnover. The main lessons learnt in the Polish project are illustrated in this presentation (from legal aspects, to the issues concerning the data transmission, passing through the problems of allocation of specific items to ECOICOP groups).
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
This paper aims at presenting the methodology developed by STATEC on how scanner data prices are planned to be introduced in the regular HICP/CPI production. Using a step-by-step approach, STATEC will start to compile sub-indices based on scanner data for a selection of sub-classes. In this paper the methodology is tested and exemplified for three COICOP sub-classes Rice, Flours and other cereals and Pasta products and couscous.
First, we provide some details regarding the method to map the products to the COICOP classification. At the elementary level, we adopt an approach where the most sold products are re-sampled every month based on a cut-off method. Thus, monthly changes will have to be chained to obtain long-term price series. We also refer to outliers whish shall be identified and treated accordingly to the situation. Moreover, imputations play an important role. We describe the imputation rules applied in our context.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
U.S. Organic Tangerine Market. Analysis and Forecast To 2025IndexBox Marketing
This report provides an in-depth analysis of the U.S. organic tangerine market. It presents the latest data of the market size and volume, domestic production, exports and imports, price dynamics and turnover in the industry. The forecast reveals market prospects to 2025.
Scanner Data
The Eurostat’s presentation makes the point about scanner data project at European level
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
In June 2014, Insee made a test on a sample of 1,000 products to check that scanner data prices are the same than collected prices. This test also showed that, in the sectors of clothing, durables goods and even manufactured goods, time series of scanner data prices have long interruptions that could be an issue in the computing of CPI for others products than food products.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
In this room document, Eurostat sketches the current situation of the NSIs about scanner data, based on the visits to Belgium, Denmark, Netherlands, Sweden, Switzerland and, Norway.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
A new methodology for processing electronic transaction data is presented, which aims at reducing the methodological differences across data sets in the Dutch CPI. Articles/GTINs are combined into “homogeneous products”, each of which is defined by a set of article characteristics. Price increases after relaunches of GTINs can be captured in this way.
Price indices are calculated as a ratio of a turnover index and a weighted quantity index. Product weights are calculated for each product from multi-period prices, which allows the timely inclusion of new products. The method does not lead to chain drift and does not require price imputations.
The new methodology is intended to replace the current sample-based methods in the CPI for a department store and for mobile phones in January 2016.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
Presentazione dello speech tenuto da Andrea De Martin (Logistics Director at OVS) dal titolo "«DIGITAL SUPPLY CHAIN»: using data optimisation and IA for improving services", durante il Decision Science Forum 2019, il più importante evento italiano sulla Scienza delle Decisioni.
The Polish project on scanner data had its first step in 2011, when the cooperation with one retail chain was established. In May 2015, the agreement with the fourth retail trade chain (the most important one) was achieved and the share covered with scanner data increased to nearly 50% of the supermarket and hypermarket in terms of turnover. The main lessons learnt in the Polish project are illustrated in this presentation (from legal aspects, to the issues concerning the data transmission, passing through the problems of allocation of specific items to ECOICOP groups).
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
This paper aims at presenting the methodology developed by STATEC on how scanner data prices are planned to be introduced in the regular HICP/CPI production. Using a step-by-step approach, STATEC will start to compile sub-indices based on scanner data for a selection of sub-classes. In this paper the methodology is tested and exemplified for three COICOP sub-classes Rice, Flours and other cereals and Pasta products and couscous.
First, we provide some details regarding the method to map the products to the COICOP classification. At the elementary level, we adopt an approach where the most sold products are re-sampled every month based on a cut-off method. Thus, monthly changes will have to be chained to obtain long-term price series. We also refer to outliers whish shall be identified and treated accordingly to the situation. Moreover, imputations play an important role. We describe the imputation rules applied in our context.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
U.S. Organic Tangerine Market. Analysis and Forecast To 2025IndexBox Marketing
This report provides an in-depth analysis of the U.S. organic tangerine market. It presents the latest data of the market size and volume, domestic production, exports and imports, price dynamics and turnover in the industry. The forecast reveals market prospects to 2025.
Scanner Data
The Eurostat’s presentation makes the point about scanner data project at European level
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
In June 2014, Insee made a test on a sample of 1,000 products to check that scanner data prices are the same than collected prices. This test also showed that, in the sectors of clothing, durables goods and even manufactured goods, time series of scanner data prices have long interruptions that could be an issue in the computing of CPI for others products than food products.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
In this room document, Eurostat sketches the current situation of the NSIs about scanner data, based on the visits to Belgium, Denmark, Netherlands, Sweden, Switzerland and, Norway.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
A new methodology for processing electronic transaction data is presented, which aims at reducing the methodological differences across data sets in the Dutch CPI. Articles/GTINs are combined into “homogeneous products”, each of which is defined by a set of article characteristics. Price increases after relaunches of GTINs can be captured in this way.
Price indices are calculated as a ratio of a turnover index and a weighted quantity index. Product weights are calculated for each product from multi-period prices, which allows the timely inclusion of new products. The method does not lead to chain drift and does not require price imputations.
The new methodology is intended to replace the current sample-based methods in the CPI for a department store and for mobile phones in January 2016.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
Presentazione dello speech tenuto da Andrea De Martin (Logistics Director at OVS) dal titolo "«DIGITAL SUPPLY CHAIN»: using data optimisation and IA for improving services", durante il Decision Science Forum 2019, il più importante evento italiano sulla Scienza delle Decisioni.
Statistics Sweden replaces traditional collection of price data with scanner data for samples of outlets and products in some parts of the consumer price index. A fixed basket approach is used, where the computing of indices is equivalent to the computing methods applied within the previous production system of the national CPI.
The use of scanner data has lowered the collection costs with annuals savings of approximately 80 000 EUR per year. In addition, the sample sizes could be increased and the standard errors of index could thereby be decreased at a low cost. About 2 000 unique products are included in 90 product groups each year, and some 100 000 price observations from scanner data are used in the Swedish CPI each month
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
The presentation introduces the discussion (developed in subgroups) about the recommendation (still to be drafted) on processing scanner data.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
The Barry Callebaut Group, the world’s leading manufacturer of high-quality chocolate and cocoa products, increased its sales volume by +8.2% to 585,620 tonnes during the first three months of fiscal year 2019/20 (ended on November 30, 2019). Sales volume in the chocolate business grew by +7.7%, well above the global chocolate confectionery market which was flat (-0.0%). Read more: http://bit.ly/2NSwHiL
Ekomilk AMP system for real time on farm milk quality and animal health controlEkomilk
Please find more recent Ekomilk AMP info on :
https://www.facebook.com/mastitismonitoring/
and
http://tumblrenglish.ekomilk.eu/
and
http://www.animalmonitoring.com/milkingrobot.html
and
http://animalmonitoring.com/EkomilkAMP_sensors_instruments_system_versions_configurations.html
-------------------------------------------------------------------------------------------------------
Introduction to the Ekomilk - AMP system for real time on farm milk quality and animal health control at approx $0.05 per test.
Intro video on Youtube:
https://www.youtube.com/watch?v=zE3_XrkW7rI
More info about Ekomilk-AMP for robotic milking (AMS, VMS etc) or other milking parlors and labs on:
http://animalmonitoring.com/
Ekomilk-AMP comprises Ekomilk Horizon , AMP and AMPI Sample Feeder for maximum automation, accuracy, measurement speed and connectivity besides workflow integration options.
--------------------------------------------
The Ekomilk AMP system for milk producers provides accurate and cost-effective (approx. 0.03$/test) somatic cell count (SCC) and fat, protein, total solid content measurement per quarter, per cow and for the dairy herd. Reliable and affordable cell count testing is now possible on every farm, in the barn, shed, stall, milking parlor besides laboratory.
With somatic cell measurement , the mammary gland infection “mastitis” of milk cows can be detected at an early stage: sub-clinical mastitis monitoring. Udder health can then properly be managed. In turn, milk production (quantity), milk quality (also important for dairy processing like cheese and yogurt) and animal well fare and longevity can be improved at the dairy farm.
Thanks to the very reliable fat, protein and total solids content measurements, true herd management is within the farm's reach, to indicate the cow's metabolics and the feeding adequacy.
Ekomilk AMP includes an easy-to-use and cost-efficient digital cell meter (somatic cell counter) and fat, protein and total solids sensors which also help reducing external milk control (DHI dairy herd improvement etc) laboratory costs. Besides individual monitoring, it is of course important to avoid a too high cell level in the milk tank (BTSCC or BMTSCC).
In this presentation ADM sketches a general framework of the situation of retail trade market in Italy within the European context. After some references to the macroeconomic context and to the forecasts, the focus is moved to household consumption model, analyzing structural trends and the impact of the crisis. Afterwards, modern retail trade in Italy is analyzed in comparison with European countries and finally the latest trends and the new challenges are briefly illustrated.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
Comprehensive scanner data (prices, quantities, turnovers) is available at the outlet level. However, certain conditions may lead compilers of price indices to deal with spatially aggregated scanner data: retail chains often want to supply information only at national and regional level, respectively, due to confidentiality reasons. NSIs might prefer to work with spatially aggregated data as it reduces the amount of data and facilitates statistical data manipulation processes. Also, retailers often claim that they set national prices for products which makes it unnecessary to analyse prices on outlet level. However, even if all outlets of a chain follow the same price policy, average outlet’s prices can be different due to different shares of sales with different discounts. Based on Austrian scanner data, the contribution explores in detail under which conditions scanner data can produce robust price indices.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
Business Intelligence: Multidimensional AnalysisMichael Lamont
An introduction to multidimensional business intelligence and OnLine Analytical Processing (OLAP) suitable for both a technical and non-technical audience. Covers dimensions, attributes, measures, Key Performance Indicators (KPIs), aggregates, hierarchies, and data cubes.
Statistics Sweden replaces traditional collection of price data with scanner data for samples of outlets and products in some parts of the consumer price index. A fixed basket approach is used, where the computing of indices is equivalent to the computing methods applied within the previous production system of the national CPI.
The use of scanner data has lowered the collection costs with annuals savings of approximately 80 000 EUR per year. In addition, the sample sizes could be increased and the standard errors of index could thereby be decreased at a low cost. About 2 000 unique products are included in 90 product groups each year, and some 100 000 price observations from scanner data are used in the Swedish CPI each month
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
The presentation introduces the discussion (developed in subgroups) about the recommendation (still to be drafted) on processing scanner data.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
The Barry Callebaut Group, the world’s leading manufacturer of high-quality chocolate and cocoa products, increased its sales volume by +8.2% to 585,620 tonnes during the first three months of fiscal year 2019/20 (ended on November 30, 2019). Sales volume in the chocolate business grew by +7.7%, well above the global chocolate confectionery market which was flat (-0.0%). Read more: http://bit.ly/2NSwHiL
Ekomilk AMP system for real time on farm milk quality and animal health controlEkomilk
Please find more recent Ekomilk AMP info on :
https://www.facebook.com/mastitismonitoring/
and
http://tumblrenglish.ekomilk.eu/
and
http://www.animalmonitoring.com/milkingrobot.html
and
http://animalmonitoring.com/EkomilkAMP_sensors_instruments_system_versions_configurations.html
-------------------------------------------------------------------------------------------------------
Introduction to the Ekomilk - AMP system for real time on farm milk quality and animal health control at approx $0.05 per test.
Intro video on Youtube:
https://www.youtube.com/watch?v=zE3_XrkW7rI
More info about Ekomilk-AMP for robotic milking (AMS, VMS etc) or other milking parlors and labs on:
http://animalmonitoring.com/
Ekomilk-AMP comprises Ekomilk Horizon , AMP and AMPI Sample Feeder for maximum automation, accuracy, measurement speed and connectivity besides workflow integration options.
--------------------------------------------
The Ekomilk AMP system for milk producers provides accurate and cost-effective (approx. 0.03$/test) somatic cell count (SCC) and fat, protein, total solid content measurement per quarter, per cow and for the dairy herd. Reliable and affordable cell count testing is now possible on every farm, in the barn, shed, stall, milking parlor besides laboratory.
With somatic cell measurement , the mammary gland infection “mastitis” of milk cows can be detected at an early stage: sub-clinical mastitis monitoring. Udder health can then properly be managed. In turn, milk production (quantity), milk quality (also important for dairy processing like cheese and yogurt) and animal well fare and longevity can be improved at the dairy farm.
Thanks to the very reliable fat, protein and total solids content measurements, true herd management is within the farm's reach, to indicate the cow's metabolics and the feeding adequacy.
Ekomilk AMP includes an easy-to-use and cost-efficient digital cell meter (somatic cell counter) and fat, protein and total solids sensors which also help reducing external milk control (DHI dairy herd improvement etc) laboratory costs. Besides individual monitoring, it is of course important to avoid a too high cell level in the milk tank (BTSCC or BMTSCC).
In this presentation ADM sketches a general framework of the situation of retail trade market in Italy within the European context. After some references to the macroeconomic context and to the forecasts, the focus is moved to household consumption model, analyzing structural trends and the impact of the crisis. Afterwards, modern retail trade in Italy is analyzed in comparison with European countries and finally the latest trends and the new challenges are briefly illustrated.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
Comprehensive scanner data (prices, quantities, turnovers) is available at the outlet level. However, certain conditions may lead compilers of price indices to deal with spatially aggregated scanner data: retail chains often want to supply information only at national and regional level, respectively, due to confidentiality reasons. NSIs might prefer to work with spatially aggregated data as it reduces the amount of data and facilitates statistical data manipulation processes. Also, retailers often claim that they set national prices for products which makes it unnecessary to analyse prices on outlet level. However, even if all outlets of a chain follow the same price policy, average outlet’s prices can be different due to different shares of sales with different discounts. Based on Austrian scanner data, the contribution explores in detail under which conditions scanner data can produce robust price indices.
http://www.istat.it/en/archive/168897
http://www.istat.it/it/archivio/168890
Business Intelligence: Multidimensional AnalysisMichael Lamont
An introduction to multidimensional business intelligence and OnLine Analytical Processing (OLAP) suitable for both a technical and non-technical audience. Covers dimensions, attributes, measures, Key Performance Indicators (KPIs), aggregates, hierarchies, and data cubes.
S. Corradini, L. Martinez, 30 Novembre - 1 Dicembre 2021 -
Webinar: L'inclusione lavorativa: il panorama nazionale e l'esperienza dell'Istat
Titolo: La condizione occupazionale delle persone con disabilità
L. Lavecchia, 30 Novembre - 1 Dicembre 2021 -
Webinar: Il quadro informativo per il Green Deal: sviluppi e domanda informativa per le questioni energetiche
Titolo: La misura della povertà energetica in Italia
V. Buratta, 30 Novembre - 1 Dicembre 2021 -
Webinar: La strategia dei dati: l’iniziativa europea e la risposta nazionale
Titolo: Il ruolo dell'Istat nella Strategia Nazionale ed Europea dei Dati
E. Fornero, 30 Novembre - 1 Dicembre 2021 -
Webinar: Gender statistics by default: il cambiamento di paradigma nelle statistiche e oltre
Titolo: Illusioni, luoghi comuni e verità nella lotta alle disparità di genere
A. Perrazzelli, 30 Novembre - 1 Dicembre 2021 -
Webinar: Gender statistics by default: il cambiamento di paradigma nelle statistiche e oltre
Titolo: Qualità di genere per sostenere la crescita
A. Tinto, 30 Novembre - 1 Dicembre 2021 -
Webinar: Gli effetti della pandemia sulla soddisfazione per la vita e il benessere: analisi e prospettive
Titolo: L'impatto della pandemia sulla componente soggettiva del Benessere Equo e Sostenibile
L. Becchetti, 30 Novembre - 1 Dicembre 2021 -
Webinar: Gli effetti della pandemia sulla soddisfazione per la vita e il benessere: analisi e prospettive
Titolo: La pandemia attraverso gli indicatori soggettivi a livello internazionale: un paradosso?
G. Onder, 30 Novembre - 1 Dicembre 2021 -
Webinar: La lezione della crisi per le statistiche demografiche e sociali
Titolo: Il sistema di sorveglianza dei decessi dell'ISS e le nuove prospettive
C. Romano, 30 Novembre - 1 Dicembre 2021 -
Webinar: La lezione della crisi per le statistiche demografiche e sociali
Titolo: Nuovi strumenti e indagini per un'informazione pertinente in fase di emergenza
S. Prati, M. Battaglini, G. Corsetti, 30 Novembre - 1 Dicembre 2021 -
Webinar: La lezione della crisi per le statistiche demografiche e sociali
Titolo: La sfida per la demografia: tempestività e qualità dell'informazione
Synthetic Fiber Construction in lab .pptxPavel ( NSTU)
Synthetic fiber production is a fascinating and complex field that blends chemistry, engineering, and environmental science. By understanding these aspects, students can gain a comprehensive view of synthetic fiber production, its impact on society and the environment, and the potential for future innovations. Synthetic fibers play a crucial role in modern society, impacting various aspects of daily life, industry, and the environment. ynthetic fibers are integral to modern life, offering a range of benefits from cost-effectiveness and versatility to innovative applications and performance characteristics. While they pose environmental challenges, ongoing research and development aim to create more sustainable and eco-friendly alternatives. Understanding the importance of synthetic fibers helps in appreciating their role in the economy, industry, and daily life, while also emphasizing the need for sustainable practices and innovation.
Macroeconomics- Movie Location
This will be used as part of your Personal Professional Portfolio once graded.
Objective:
Prepare a presentation or a paper using research, basic comparative analysis, data organization and application of economic information. You will make an informed assessment of an economic climate outside of the United States to accomplish an entertainment industry objective.
The French Revolution, which began in 1789, was a period of radical social and political upheaval in France. It marked the decline of absolute monarchies, the rise of secular and democratic republics, and the eventual rise of Napoleon Bonaparte. This revolutionary period is crucial in understanding the transition from feudalism to modernity in Europe.
For more information, visit-www.vavaclasses.com
Honest Reviews of Tim Han LMA Course Program.pptxtimhan337
Personal development courses are widely available today, with each one promising life-changing outcomes. Tim Han’s Life Mastery Achievers (LMA) Course has drawn a lot of interest. In addition to offering my frank assessment of Success Insider’s LMA Course, this piece examines the course’s effects via a variety of Tim Han LMA course reviews and Success Insider comments.
Operation “Blue Star” is the only event in the history of Independent India where the state went into war with its own people. Even after about 40 years it is not clear if it was culmination of states anger over people of the region, a political game of power or start of dictatorial chapter in the democratic setup.
The people of Punjab felt alienated from main stream due to denial of their just demands during a long democratic struggle since independence. As it happen all over the word, it led to militant struggle with great loss of lives of military, police and civilian personnel. Killing of Indira Gandhi and massacre of innocent Sikhs in Delhi and other India cities was also associated with this movement.
Acetabularia Information For Class 9 .docxvaibhavrinwa19
Acetabularia acetabulum is a single-celled green alga that in its vegetative state is morphologically differentiated into a basal rhizoid and an axially elongated stalk, which bears whorls of branching hairs. The single diploid nucleus resides in the rhizoid.
Introduction to AI for Nonprofits with Tapp NetworkTechSoup
Dive into the world of AI! Experts Jon Hill and Tareq Monaur will guide you through AI's role in enhancing nonprofit websites and basic marketing strategies, making it easy to understand and apply.
Welcome to TechSoup New Member Orientation and Q&A (May 2024).pdfTechSoup
In this webinar you will learn how your organization can access TechSoup's wide variety of product discount and donation programs. From hardware to software, we'll give you a tour of the tools available to help your nonprofit with productivity, collaboration, financial management, donor tracking, security, and more.
A Strategic Approach: GenAI in EducationPeter Windle
Artificial Intelligence (AI) technologies such as Generative AI, Image Generators and Large Language Models have had a dramatic impact on teaching, learning and assessment over the past 18 months. The most immediate threat AI posed was to Academic Integrity with Higher Education Institutes (HEIs) focusing their efforts on combating the use of GenAI in assessment. Guidelines were developed for staff and students, policies put in place too. Innovative educators have forged paths in the use of Generative AI for teaching, learning and assessments leading to pockets of transformation springing up across HEIs, often with little or no top-down guidance, support or direction.
This Gasta posits a strategic approach to integrating AI into HEIs to prepare staff, students and the curriculum for an evolving world and workplace. We will highlight the advantages of working with these technologies beyond the realm of teaching, learning and assessment by considering prompt engineering skills, industry impact, curriculum changes, and the need for staff upskilling. In contrast, not engaging strategically with Generative AI poses risks, including falling behind peers, missed opportunities and failing to ensure our graduates remain employable. The rapid evolution of AI technologies necessitates a proactive and strategic approach if we are to remain relevant.
Model Attribute Check Company Auto PropertyCeline George
In Odoo, the multi-company feature allows you to manage multiple companies within a single Odoo database instance. Each company can have its own configurations while still sharing common resources such as products, customers, and suppliers.
Belgian scanner data project: methodology and results - Ken Van Loon, François Valenduc
1. Belgian Scanner Data Project
Methodology and results
Rome
1&2 October
François Valenduc & Ken Van Loon
Statistics Belgium
2. http://statbel.fgov.be
Contents
Overview of the project
Combining scanner data and classical price collection
– Link to COICOP
– Stratification model
Methodology for calculating scanner data indices
Results
– Unit value versus observed price
– Experimental indices
Future developments
3. http://statbel.fgov.be
Scanner data: overview of the project
We receive scanner data from the 3 largest supermarket chains in
Belgium: Colruyt, Carrefour and Delhaize (around 75% of the market)
Negotiations started early 2012
We received our first scanner datasets by the end of 2013
– Historical data for Colruyt and Carrefour starting from January 2012
– Historical data were received from Delhaize starting from January 2013
Each week we receive the data of the previous week via SFTP:
– On Tuesday for Colruyt and Carrefour (+ 2 days)
– The following weekend for Delhaize (+ 7 days)
The data we receive can be split into 2 parts
– One dataset containing the product info
– One dataset containing the internal classification of the retail chain
Currently, scanner data are used in 9 COICOP 5 groups in the CPI,
implementation in the HICP/CPI starting in 2016 for at least COICOP 1
4. http://statbel.fgov.be
Scanner data: link to COICOP
First step: link the internal classification to COICOP 5 digits
Second step: create detailed groups at COICOP 6 digits
(consumption segments)
– Not the same segments as we use for classical price collection
– Turnover information from scanner data shows that the current sample is
not always representative
– Groups at COICOP 6 digits are harmonised as much as possible between
the different retail chains to allow for comparison
– Around 450 COICOP 6 digits groups for COICOP 01 instead of 173 for
classical price collection
Maximal use of internal classification of retail chains
– Each chain has around 3500 internal groups
• Often too detailed to use this directly (e.g. one product per group !)
• Sometimes, internal groups are quite heterogeneous
• Linking at product level is inevitable in order to create groups at COICOP 6 level :
around 10% of the products are individually linked
– Currently examining whether machine learning (using supervised learning
models) can be used.
5. http://statbel.fgov.be
To combine scanner data and classical price collection a
stratification model is used. Indices are always combined at the
COICOP 5 digits level.
Aggregation based on
expenditures by retail
channel (HBS)
Speciality stores –
COICOP 5
Discounter – COICOP 5Supermarkets– COICOP 5
Aggregation based on
turnover
Supermarkets and discounters –
COICOP 5
Global index – COICOP 5
Scanner data and classical price
collection: stratification
6. Scanner data and classical price
collection: stratification
http://statbel.fgov.be
Scanner
data
COICOP 6
group 1
Jevons index
Scanner
data
COICOP 6
group 2
Scanner
data
COICOP 6
group 3
Scanner
data
…
Retail chain 1 –
COICOP 5
Aggregation based on
turnover from scanner
data
Retail chain 2 –
COICOP 5
Retail chain 3 –
COICOP 5
Supermarkets– COICOP 5
Aggregation based on
turnover from annual
accounts
7. http://statbel.fgov.be
Scanner data and classical price
collection: stratification
Groups where prices of retail chains, discounters and speciality stores
are combined (based on data from HBS 2012):
For other COICOP groups in COICOP 1 (where market share is below
15% for speciality stores), limitation to scanner data and discounters.
– Our own research shows a high correlation between supermarkets and speciality
stores for those groups
COICOP Supermarkets & discounters Speciality stores
01.1.1.3 Bread 54% 46%
01.1.2.8 Other meat preparations 74% 26%
01.1.2.1 Beaf and veal 76% 24%
01.1.2.5 Other meat 76% 24%
01.1.2.2 Pork 78% 22%
01.1.2.7 Dried, salted or smoked meat 79% 21%
01.1.1.4 Other bakery products 80% 20%
01.1.2.3 Lamb and goat 81% 19%
01.1.2.4 Poultry 84% 16%
8. http://statbel.fgov.be
Based on methods of the Netherlands and Switzerland
– use of monthly chained Jevons index at COICOP 6 digits level
– sampling: product included in the sample if
𝑠 𝑚+𝑠 𝑚−1
2
>
1
1.25 × 𝑛
with n = number of products and sm (or sm-1) = market shares of each
product
– price imputation for temporary missing products or out of sample products
(to satisfy the identity and transitivity test)
– dumping and outlier filters
– prices that are excluded by dumping and outliers filter are also imputed
– unit value price for each internal code is used (normally first 3 weeks of a
month)
Calculation is done in SAS
Products falling out of the sample are verified against products
entering the sample to check if product relaunches occur:
– Direct comparison (if necessary with volume adjustment) in the case of
product relaunches
– Same system for volume discounts: most of the time, products with volume
discounts (6 + 2 free) have different internal codes
Scanner data: methodology
9. http://statbel.fgov.be
Scanner data: linking (relaunches)
Each month two lists are generated for every COICOP 6 digits group of
every retail chain:
– One list contains the “new” products in the sample
– Another lists contains the products that have disappeared from the sample in the
current month and the previous 3 months (also the turnover figures are listed)
In order to avoid a possible bias in the index level the old product and
new product are linked if they refer to the same product (if necessary,
volume adjustment is done)
Around 80 linkings per month for COICOP 1
Currently this linking is done manually in MS Access .
We are doing research on text mining (fuzzy matching) to see if this
can be done more efficiently
Month COICOP Group Old product New product Coeff.
June-14 01.1.1.4.02
Chocolate
biscuits
LU PRINCE - 6 + 2 gratis -
Mini Stars B & W
LU PRINCE - 225 g - Mini
Stars Black & White
0.75
October-14 01.1.4.5.10 Cream cheese
KRAFT PHILADELPHIA - 200 g
- fromage light
KRAFT PHILADELPHIA -
300 g - fromage light
1.50
11. http://statbel.fgov.be
Scanner data – Use of internal codes
Use of internal code to match products instead of GTIN (or EAN)
– The internal code can also be used to verify the product on the website
of the retail chain (useful for making a link between new and old
products or for purchasing power parities)
• The product description we receive is usually also the one used on
the website, since this description is the most detailed.
– Fresh products such as meat, fruits and vegetables are sold in different
quantities, everything is aggregated with one internal code to get for
example the average price per kilo of “chateaubriand steak”
– GTIN are often reused for totally different product for in-store EANS:
– GTIN codes are only used to verify the consistency in the link to the
COICOP classification between the different retail chains
Date GTIN Internal code Description
1/01/2013 2020380000000F1988111800338400000 Melon | Charentais | Philibon
2/03/2015 2020380000000F1986053100318010000 Green pepper | Sold loose
12. http://statbel.fgov.be
Scanner data – example multiple GTIN codes
Example of multiple GTIN-codes for
the same product
For instance, Ferrero Rocher is sold
under two GTIN codes at one chain:
– 8000500032237
– 8000500167113
– But only one internal code S2001062000072760000
When it’s available under the 2 codes, the unit value is identical
(5,99 €):
Week GTIN Internal code Product description Unit Sales unit Turnover Unit value
07Oct20138000500032237 S2001062000072760000 Rocher | 30 pièces | Ferrero 0.375K 475 2845.25 5.99
07Oct20138000500167113 S2001062000072760000 Rocher | 30 pièces | Ferrero 0.375K 732 4381.69 5.99
17. http://statbel.fgov.be
Examples
Some examples: scanner data indices compared to traditional price
collection for the period 12/2013 - 07/2015
Traditional price collection limited to the 3 chains for which we receive
scanner data
Number of products used in the calculation (scanner data):
COICOP Group Number of products
01.1.1.6 Pasta products and couscous 689
01.1.4.1 Whole milk 47
01.1.4.2 Low fat milk 124
01.1.4.5 Cheese 1440
22. http://statbel.fgov.be
– Compilation of HICP CT using scanner data: excise taxes depend on
volume and alcoholic grade: some assumptions or simplification may be
needed (also done at the moment for manual price collection).
– Negotiations with Lidl (currently in progress) and Aldi (around 16% of
market share together)
– Negotiations with consumer electronics or clothing stores
– Research on machine learning for link to COICOP
– Research on text mining to detect product relaunches
Future developments
23. Thanks for your attention
Questions ?
http://statbel.fgov.be