QuantZ uses machine learning to create plug-and-play Composite Signals constructed from the ESBs, as presented below. They highlight curated factor portfolios i.e., Composite Signals based on ESB combos. Given that the set of N choose k combinations in this case is quite large, consider focusing on the curated composites they have created for each factor family and the subsequent ESB combos.
Recall that published ESB spreads are based on the best of five methodologies (as regards aggregation of factors within the Smart Beta cohorts) where the winner is defined by the highest cumulative return LTD for each ESB:
- Equal Weighted
- Max Sharpe Ratio optimization (on an expanding window to prevent look ahead bias)
- Risk Parity optimization (on an expanding window to prevent look ahead bias)
- Top 3 factors based on cumulative return but Equal Weighted (on an expanding window to prevent look ahead bias)
- Top 3 factors based on Sharpe ratio but Equal Weighted (based on cumulative return on an expanding window to prevent look ahead bias)
Subsequently, we take Equal Weighted combos (for the winning flavor of each ESB) to obtain our Composite Signal Monitor:
Composite Signal Definitions
Type I: (EW combos of ESBs based on the best flavor)
Value Composite: DV + RV
Growth+Momentum Composite: ARS + ART + EnMOM + GroH
Quality Composite: CSU + Eff + EQ + Lev + Stab + Prof
Fabulous Fourteen: ARS + ART + CSU + DV + Eff + EnMOM + EQ + GroH + Lev + Prof + Rev + Risk + RV + Size
Enterprise Eighteen: All 18 ESBs
Type II: (EW combos of EW combos)
Value Momentum Composite: Value Composite + Growth+Momentum Composite
Quality Value Composite: Quality Composite + Value Composite
Quality Momentum Composite: Quality Composite + Growth+Momentum Composite
Type III: (EW combos of EW combos & ESBs based on the best flavor)
Famous Five: Quality Composite + Value Composite + Growth+Momentum Composite + Risk + Size
Sizzling Seven: Quality Composite + Value Composite + Growth+Momentum Composite + Risk + Size + Rev + SIRF
Enhanced Smart Beta Definitions
ARS: This smart beta composite shows our Analyst Revisions cohort based on measures of estimate revisions, dispersion, Standardized Unexpected Earnings surprise (SUE score) & consensus change in both earnings as well as revenues which can outperform traditional metrics like a 1mo consensus change.
ART: This smart beta composite shows our Analyst Ratings & Targets cohort based on measures of analyst recommendations, target price, changes & diffusion which can outperform traditional metrics like a 1mo consensus change.
CSU: This smart beta composite shows our Capital Structure/Usage cohort based on measures including Buybacks, Total yield, Capex, capital usage ratios etc which can outperform traditional metrics like Cash/MC.
Dividends: This smart beta composite shows our Dividends related cohort based on measures including Yield, payout, growth, forward yield etc which can outperform traditional metrics like Dividend Yield.
DV: This smart beta composite shows our Deep Value (or intrinsic value) cohort based on measures including tangible book & sales which can outperform traditional Book yield.
Efficiency: This smart beta composite shows our Efficiency cohort based on measures including Asset Turnover, Current Liabilities, Receivables etc which can outperform traditional metrics like Asset Turnover.
EnMOM: This smart beta composite shows our Enhanced Momentum cohort which can outperform traditional 12 month price momentum in both return & risk adjusted terms particularly at market inflection points.
EQ: This smart beta composite shows our Earnings Quality cohort based on a variety of Accrual measures which can outperform traditional metrics like Total Accruals.
Growth: This smart beta composite shows our Historical Growth cohort based on a variety of Earnings, Sales, Margins & CF related growth measures which can outperform traditional metrics like 3yr Sales growth.
Leverage: This smart beta composite shows our Leverage related cohort based on measures of Balance Sheet leverage which can outperform traditional metrics like Debt To Equity.
PMOM: This smart beta composite shows our PMOM related cohort which can outperform traditional 12 month price momentum using a variety of traditional momentum factors.
Profit: This smart beta composite shows our Profitability cohort based on measures like ROA, ROE, ROCE, ROTC, Margins etc which can outperform traditional metrics like ROE.
RV: This smart beta composite shows our Relative Value cohort based on measures of EPS, CFO, EBITDA etc which can outperform traditional Earnings yield.
Reversals: This smart beta composite shows our Reversals cohort which is comprised of metrics like short term reversals, RSI, DMA & other technical factors which can outperform traditional metrics like a 1 month total return.
Risk: This smart beta composite shows our Risk/ Low Vol cohort which is comprised of metrics like Beta, Low volatility etc.
SIRF: This smart beta composite shows our Short Interest cohort which is comprised of metrics related to Short Interest and its normalization by Float, trading volume etc.
Size: This smart beta composite shows our Size cohort which is comprised of metrics related to firm size including market capitalization.
Stability: This smart beta composite shows our Stability cohort which is comprised of metrics like Dispersion of EPS/ SPS estimates as well as the stability of Margins, EPS & CFs etc.
EXPLANATORY FOOTNOTES:
Factor portfolios are not sector neutral.
Generated weekly as of last night’s close this report shows the DTD, MTD, YTD and LTD returns for our smart beta composite spreads.
Factors within the cohort spreads are long-short based on top vs bottom 5%-tile (~125×125) of the largest liquid US traded stocks (usually ~2500 depending upon market capitalization & minimum $ price criterion for stocks listed on NYSE & Nasdaq).
Certain industries like Biotechs and REITS are excluded due to event risk or because a generic quant model is not appropriate for those industries.
Individual factor top & bottom portfolios are equally weighted 5%-tiles. While the combined ESB spreads also represent top vs bottom 5%-tiles they are based on the best (cumulative return LTD) of five methodologies listed above.
MTD returns/ spreads are geometrically chain-linked DTD returns/ spreads where both are based on factor portfolios formed at the prior month end close.
YTD & LTD returns are based on geometric chain-linking of monthlies without transaction costs or fees as is customary in the factor literature.
Multi-period spread returns are not the difference of cumulative top vs bottom returns. Instead, they represent the daily geometrically compounded & rebalancing of the market neutral “active return” differential of the top vs bottom portfolios.
Both Max Sharpe & Risk Parity optimization routines are based on a Hybrid methodology where we 1] find the optimal factor mix within the Smart Beta cohort based on signal blending/ “mixing” but 2] subsequently run the combined ESB spreads outsample on a fully “integrated” basis not just as the linear combination of factor returns.
LTD data commences January 2000.
