US Nonfarm Employment Prediction Using RIWI Corp. Alternative Data

By Ernest Chan

Figure 1: Weighted monthly RIWI score, without seasonal adjustments, including only “Full-Time” respondents, for Dec 2013-Oct 2017 and Sep 2018-Sep 2019.
Figure 2: Weighted monthly RIWI score, without seasonal adjustments, including “Full-time + part-time” respondents, for Dec 2013-Oct 2017 and Sep 2018-Sep 2019.
  • Previous 12-month NFP surprise
  • Bloomberg Barclays US Corporate High Yield Average Option Adjusted Spread Index (a.k.a. credit spreads)
  • Index of Consumer Sentiment (University of Michigan)
  1. Trend-following model predicts next sign(surprise)=sign(previous surprise).
  2. Contrarian model predicts next sign(surprise)=-sign(previous surprise).
  3. Logistic regression on credit spreads.
  4. Logistic regression on Index of Consumer Sentiment.
Table 1: Classification benchmarks and other features
  1. Trend-following model predicts next surprise=(previous surprise).
  2. Contrarian model predicts next surprise=-(previous surprise).
Table 2: Regression benchmarks

No Code Financial Machine Learning SaaS that helps traders compute the probability of profit for their next trade or the daily risk for their strategy.