Using Data from Digital Traces Bradley R. Staats Visiting Associate Professor, The Wharton School University of Pennsylvania Associate Professor, UNC Kenan-Flagler Trace data: A sign or evidence of some past thing http://hadoopilluminated.com/hadoop_illuminated/Big_Data.html 1. Introduction 2. Examples 3. Issues to Consider 1. Digital trace: Process data Application received & scanned Custodian Yes Document Tagging Application Capture (1 & 2) Yes Preliminary Information (1 & 2) Policy fail? No No Automatic incomplete application letter No 111 workers over 2 ½ years 598,393 individual transactions Additional Application Capture (1 & 2) Document Tagging Yes Materials received & scanned Custodian Application Complete? Yes Credit Check (1 & 2) Automatic request for additional materials No Yes Policy fail? No Application Complete? No Automatic incomplete application letter Marginal Yes Policy fail? No Automatic rejection letter sent Income Tax (1 & 2) Policy fail? No Real Estate (1 & 2) Routed to credit expert for negotiation Credit Approval Yes Yes No Yes 1. Introduction 2. Examples Automatic approval letter sent 3. Issues to Consider Automatic Automatic rejection letter rejection letter sent sent A perennial problem in industry has been that of sustaining human productivity over extended periods of time. –Scott 1966: 4 Specialization (Smith 1776; Taylor 1911; Skinner 1974; Boh et al. 2007; Schultz et al. 2003) Variety Task Allocation Strategy? (Hackman & Oldham 1976; Schilling et al. 2003; Narayanan et al. 2009) Findings • During a day: Specialization > Varied assignment • Across days: Varied assignment > Specialization • Workers exhibit learning in setups Staats & Gino (2012). Specialization and variety in repetitive tasks: Management Science. 2. Digital trace: Click data 1. Introduction 2. Examples 3. Issues to Consider 2. Digital trace: Click data How does the team encourage (or discourage) individual knowledge sourcing behavior? • Knowledge repository data – Per-click data by person • Software development project data – Project outcomes, characteristics – 487 projects • HR system data – E.g., demographics 1. Introduction 2. Examples 3. Issues to Consider 3. Digital trace: Search data • Do temporal landmarks motivate aspirational behavior Google searches for “diet” (average) 75 75 70 65 60 55 50 Mon Tue Wed Thu Fri Day of the Week First workday after federal holidays 70 65 60 55 50 Sat Sun -4 -3 -2 -1 0 1 2 3 Days Since the First Workday After a Federal Holiday 4 Dai, Milkman & Riis (Forthcoming). The Fresh Start Effect. Management Science. 1. Introduction 2. Examples 3. Issues to Consider 4. Digital trace: Tracking data RFID tags monitoring hand washing compliance Personalized messaging Data transfer to a central server 13,773,068 hand hygiene opportunities • Generated by 4,157 caregivers at 35 hospitals from January 2010 to March 2013 Dai, Hengchen, Milkman, Katherine L., Hofmann, David A., & Staats, Bradley R. The Impact of Time at Work and Time off from Work on Rule Compliance: The Case of Hand Hygiene in Healthcare. 1. Introduction 2. Examples 3. Issues to Consider 4. Digital trace: Tracking data How do job demands affect individual compliance over the course of a single shift? Dai, Hengchen, Milkman, Katherine L., Hofmann, David A., & Staats, Bradley R. The Impact of Time at Work and Time off from Work on Rule Compliance: The Case of Hand Hygiene in Healthcare. 1. Introduction 2. Examples 3. Issues to Consider Issues to Consider • Access – Relationship building – Pipeline management • Structure to the data • Mechanisms – Mixing other methods – Or maybe leveraging more trace data… • Informed consent 1. Introduction 2. Examples Myers, Chris, Staats, Bradley R., & Gino, Francesca. “My Bad”: The Impact of Internal Attribution and Ambiguity of Responsibility on Learning from Failure. 3. Issues to Consider