Billion Prices Proj ect: Avoiding the Big Data – Small Info S yndrome Roberto Rigobon MIT S loan, NBER, CS AC
Big distance between Data and Information! The world is not lacking of data, it’s lacking of information Need a question before collection Data without purpose, produces problems not information Great Data is not a licenses for Bad Econometrics Need to understand phenomena Measuring is not Predicting Correlations are hardly Causal
Inflation and Price Indexes Albert o Cavallo We want t o produce alt ernat ive measures of inflat ion We need prices We need methodology to weight those prices We need to understand product introductions and discontinuations We need to understand store behavior How to collect prices of products not sold on the internet? S ervices?
Online Information and Indexes Our Approach to Daily Inflation S tatistics 1 2 3 4 5 Use scraping Connect t o Find individual S t ore and Develop daily t echnology t housands of it ems process key it em inflat ion online ret ailers informat ion in a st at ist ics for ~20 every day dat abase count ries • Dat e • It em • Price • Descript ion
How do we collect data? Our prices are collected from public online sources, using a technique called “ web scraping ” A software downloads a webpage, analyses the html code, “ scrapes ” price data, and stores it in a database
Countries covered
Properties of Inflation Indexes Congruence S tores keep markups between online and offline prices relatively constant in the medium run Anticipation Online Price Indexes trends anticipate official inflation shifts. Online prices are easier to change, retailers are more competitive, and consumers have less memory. Demand trends Changes in inflation trends by retailers reflect changes in the demand they are facing
Argentina
US A
US Recession S ep 16 2008
US 2012
Annual Inflation Rates China – S upermarket Index Argentina Australia Colombia Germany Ireland Venezuela UK Russia
Other Indexes Nat ural Disast er’s Measurement Employment Real Est at e Inflat ion and Capit al Gains GDP and Economic Act ivit y
Thailand: When Help S hould Be Deployed? Product Availability In Online Retailers 120 100 80 60 40 20 0 10/ 1 10/ 2 10/ 3 10/ 4 10/ 5 10/ 6 10/ 7 10/ 8 10/ 9 10/ 10 10/ 11 10/ 12 10/ 13 10/ 14 10/ 15 10/ 16 10/ 17 10/ 18 10/ 19 10/ 20 10/ 21 10/ 22 10/ 23 10/ 24 10/ 25 10/ 26 10/ 27 10/ 28 10/ 29 10/ 30 10/ 31 Not es: Product Availabilit y normalized t o 100 on 10/ 1/ 2011
Recommend
More recommend