How the D&B Data Cloud Helps Predict Stock Returns
Dun & Bradstreet has the largest global commercial database on the planet. At the core is proprietary trade payment data collected from thousands of trade suppliers, which is closely related to account payables on company’s balance sheet. The Credit Score Archive Database (CSAD, 2004-2016) is directly derived from the raw trade payment data, and has about 140 attributes including a company’s payment behavior and various risk assessments. We’ve applied a statistically rigorous process to identify top attributes that have predictive power in separating cross-sectional stock returns – some of the attributes are further transformed to make suitable for testing. In each document, we present one attribute for illustration purposes. The attribute shows from a unique and proprietary angle how the D&B Data Cloud and analytics helps to enhance stock returns. The complete list of attributes identified, with test statistics, is available upon request.
“High Relative Trade Credit Underperforms”:
Dun & Bradstreet found that stocks with high relative trade credit (to sales) underperform those with low relative trade credit. The underperformance is statistically significant after adjusting for the Fama-French 3-factor model + MOM (aka FF3+MOM). Download whitepaper.
“The Hidden Cost of Growing Trade Supplier Networks Too Fast”:
Dun & Bradstreet found that stocks with the fastest growing number of trade suppliers year over year underperform those with slowest growing trade suppliers. The underperformance is statistically significant after adjusting for the Fama-French 3-factor model + MOM (aka FF3+MOM). Download whitepaper.
“When Slow or Negative Payment Experiences Accelerate”:
Dun & Bradstreet found that stocks with the fastest increase in the number of slow or negative payment experiences month over month underperform those with slowest increase. The underperformance is statistically significant after adjusting for the Fama-French 3-factor model + MOM (aka FF3+MOM). Download whitepaper.
Summary of Stock Market Insights
When companies have increasing pexp_s_n month over month, i.e. positive pexp_s_n_.pc, it is a sign of deteriorating short-term cash flow. Conversely, negative pexp_s_n.pc is an indication of improving short-term cash flow. Here, we study how companies with high pexp_s_n.pc perform versus those with low pexp_s_n.pc, and versus the stock market index. The universe is the S&P Total Market Index (S&P TMI), from 2005 – 2016. At the end of month T we rank stocks in the universe based on ranking sorted by pexp_s_n.pc, and compare the top x% with bottom x%, on the total return for month T+1.
TABLE 1 show that companies increasing pexp_s_n the fastest, underperform those increasing the slowest (or decreasing the fastest), by 23 bps per month (top 5% vs bottom 5%); or by 37 bps per month (top 10% vs bottom 10%), etc.
Table 1: TMI is the S&P Total Market Index; pcThr is the percentage threshold used in constructing long/short portfolio; Spread is the return difference between top and bottom group; StdErr, tStat, pVal, Conf are standard error, t-statistics, p-value, and confidence interval of the Spread; Mth is the total number of months tested; numL, numS are the average number of stocks in the Long (top group) and Short (bottom group) portfolio.
TABLE 2 shows that after removing exposure from the FF3 + MOM, the spread shows -23 bps alpha monthly (top 5% vs bottom 5%), or -37 bps (top 10% vs bottom 10%).
Table 2: Performance difference between top and bottom group. pcThr: is the percentage threshold use in constructing long/short portfolio; xRet is the alpha (excess return) after adjusting for the FF3 + MOM; vMxF, vSMB, vHML, vMom are the portfolio exposure to the FF3 + MOM. The t-stat of the coefficients are in parenthesis.
The chart below shows the cumulative performance of the inversed alpha in Table 2.