The Big Macro Nowcasting RankingList of forecasting modelsAcronymModel DescriptionAR(P)Autoregressive iterated-specificationRWRandom walkARDI(K,BIC)Autoregressive diffusion indices with K factors. Optimal lag-order via BICT.ARDI(K,BIC)ARDI with target-factors. Hard-threshold set to |t-stat|>1.96BVAR-MinnHomoscedastic large Bayesian VARBVAR-CSVLarge Bayesian VAR with heteroscedastic innovationsBBoostQuadratic-loss L2 boosting, block-wiseCBoostQuadratic-loss L2 boosting, component-wiseCSRComplete Subset Regressions (20C4) with hard-thresholding preselectionBagLinear bagging with hard-thresholding preselectionBTreeBoosting regression treesRFRandom forestsSVRSupport vector machine regression with Gaussian Kernel functionRidgeRidge regressionLASSOLeast absolute shrinkage and selection operator with BIC for lambdaAdaLASSOAdaptive LASSOENElastic NetAdaENAdaptive ENLSTMLong-short-term memory RNN with 3-hidden layersSgLASSOSparse-group-LASSO-MIDAS with block-K-fold CV for lambda & alphaList of methods for treating mixed-frequenciesAcronymTransformation DescriptionD1Down-sampling to Quarterly (Temporal aggregation with equal-weights)D2Unrestricted MIDAS PolynomialsD3Legendre Polynomials (3rd degree)The Ranking: Real-time model evaluationModelsn=0n=1n=2n=3n=4avgBag-D30.7280.9320.9720.9980.9940.925CSR-D20.7070.9380.97611.0040.925BBoost-D1F0.7250.9250.9781.0061.0010.927Bag-D2F0.7720.910.9670.9940.9990.929Ridge-D10.7640.9240.9580.9961.0010.929Ridge-D20.7420.9260.9721.0011.0050.929Bag-D20.7670.9210.9690.9931.0020.93T.ARDI(2)0.7450.9290.9751.0021.0070.932Bag-D1F0.7590.9250.971.0051.0010.932Bag-D10.7830.9180.9610.9961.0020.932CSR-D10.7580.9340.9741.0041.0090.936Ridge-D30.7910.9210.9691.0041.0030.938RF-D1F0.8160.9170.9660.9950.9920.938Ridge-D2F0.8080.9130.9680.9991.0040.938CBoost-D1F0.7730.9250.9831.011.0010.938SVR-D10.8250.9190.9640.9920.9950.939LASSO-D1F0.7870.930.9781.0020.9990.939AdaLASSO-D1F0.7810.9370.981.0030.9980.94RF-D10.8040.9240.9710.9991.0030.94Bag-D3F0.8160.9170.9721.0050.9930.941EN-D2F0.8160.9210.9690.9991.0010.941EN-D1F0.7990.9280.9781.00110.941SVR-D30.8270.920.970.9950.9970.942RF-D30.8120.9360.9690.9941.0010.942ARDI(1)0.7990.9390.9750.9991.0010.943CBoost-D2F0.8210.920.9650.9991.0080.943BBoost-D2F0.8360.9120.9670.99810.943SVR-D3F0.8310.9140.9720.9951.0010.943SVR-D20.8280.9230.9710.9970.9970.943AdaEN-D20.7660.9470.9771.0031.0240.943EN-D20.7770.9710.9780.9960.9940.943RF-D20.8160.9250.9761.00110.943LASSO-D2F0.8310.920.9690.99810.944AdaEN-D1F0.8020.9340.9811.00210.944SVR-D1F0.8270.9210.9710.99910.944CSR-D2F0.8240.9280.970.99710.944SVR-D2F0.8310.9250.9720.9960.9950.944RF-D2F0.8270.9290.9720.9980.9950.944BTree-D1F0.8110.9230.9751.0021.0080.944AdaEN-D2F0.8340.9260.9650.9991.0020.945AdaLASSO-D2F0.840.9220.9660.9981.0010.945AdaLASSO-D20.7650.9540.9790.9981.0340.946LSTM-D1F0.8450.9180.9681.0050.9940.946ARDI(2)0.7980.9470.9781.0011.0080.946EN-D30.8340.9240.975110.947CSR-D30.8140.9310.981.0051.0030.947RW0.8390.9210.9750.9990.9990.947LSTM-D2F0.8440.9280.96610.9970.947LASSO-D20.780.980.98310.9970.948BVAR-CSV0.8110.9260.981.0121.0130.948RF-D3F0.8440.9340.9760.9911.0010.949T.ARDI(1)0.8140.9480.9751.0051.0070.95AdaEN-D10.8170.9310.9911.0071.0030.95BBoost-D3F0.8650.9060.9731.0061.0010.95AdaEN-D30.8480.9280.97611.0020.951LSTM-D3F0.8510.9260.9720.9941.0130.951SgLASSO-D30.8490.9250.9781.0031.0050.952SgLASSO-D3F0.8610.9120.9771.0111.0030.953CSR-D1F0.8770.9250.970.9980.9990.954EN-D10.8090.9360.9441.0451.0360.954BTree-D10.8120.9330.9881.0151.0240.955AdaEN-D3F0.8830.9240.9681.0010.9990.955LSTM-D30.8580.9320.9781.0051.0040.955BVAR-Minn0.850.9330.9741.0121.0150.957EN-D3F0.8910.9260.97110.9990.957CBoost-D3F0.8540.9360.9851.0131.0010.958LSTM-D10.8660.9360.9781.0021.0130.959CSR-D3F0.890.9380.971.0010.9970.959LASSO-D3F0.9030.9210.97111.0030.96AdaLASSO-D3F0.8930.9290.9711.0031.0040.96BTree-D2F0.850.9540.9911.0170.9970.962LSTM-D20.8680.9430.9861.0170.9990.962BTree-D20.8390.9520.9941.0121.0160.963Ridge-D3F0.8020.9411.0171.0461.0330.968AdaLASSO-D10.830.9471.0191.0371.0220.971BTree-D30.8510.9880.991.0161.0210.973Ridge-D1F0.7790.9591.0261.061.0540.976LASSO-D30.8320.9321.0181.061.0560.98AdaLASSO-D30.8340.9451.031.0651.060.987LASSO-D10.7741.0070.9871.1021.0740.989BTree-D3F0.881.0310.9991.011.0330.991AR(BIC)1.0081.00311.00111.002AR(CV)1.021.00411.0010.9991.005AR(4)1.0491.0171.0020.9990.9991.013AR(1)NaNNaNNaNNaNNaNNaNAutomaticThe Big Macro Nowcasting RankingThe objective of this page is to maintain and populate the ranking below, with newly introduced statistical models in an effort to provide a continuously updated comprehensive comparison of methodologies for nowcasting and forecasting macroeconomic activity. The model comparison is based on a set of (pseudo) real-time vintages, formed using a rich standardized set of variables at mixed-frequencies.The performance evaluation currently covers US real GDP growth rate (QoQ%), comparing 20 distinct methodologies (including ML, as well as standard econometric techniques and workhorse benchmarks), which are combined with three data transformations (D1,D2,D3) for taking into account the mixed-frequency dimension. This results into a ranking containing a total of 85 specifications.The dataset consists of 87 quarterly, and 171 monthly (including 31 financial market) indicators. The indicators correspond to the series found in the FRED-MD and -QD datasets and were downloaded at their original (i.e. highest-available) sampling frequency, whenever possible. Publication release delays were inferred from the metadata in the FRED database (https://fred.stlouisfed.org) and then applied to each series to mimic the ragged-edge structure the forecaster would face in reality. The out-of-sample evaluation uses end-of-month vintages at a monthly periodicity, assuming that economic activity is monitored in \textit{real-time} by updating the projections at the end of every month.A list of the indicators that compose the mixed-frequency dataset, can be accessed +here. +SeriesID refers to the FRED mnemonic, while the release delay (RDelay) measures the approximate number of days it takes for the respective indicator to be released after the closing of the reference month or quarter. The monthly mixed-frequency vintages used in the POOS model evaluation can be downloaded here. The full set consists of 376 end-of-month vintages spanning the period 19900131-20210430, including monthly and quarterly unbalanced panels whose ragged edge has been imposed by applying the inferred publication delays.List of forecasting modelsAcronymModel DescriptionAR(P)Autoregressive iterated-specificationRWRandom walkARDI(K,BIC)Autoregressive diffusion indices with K factors. Optimal lag-order via BICT.ARDI(K,BIC)ARDI with target-factors. Hard-threshold set to |t-stat|>1.96BVAR-MinnHomoscedastic large Bayesian VARBVAR-CSVLarge Bayesian VAR with heteroscedastic innovationsBBoostQuadratic-loss L2 boosting, block-wiseCBoostQuadratic-loss L2 boosting, component-wiseCSRComplete Subset Regressions (20C4) with hard-thresholding preselectionBagLinear bagging with hard-thresholding preselectionBTreeBoosting regression treesRFRandom forestsSVRSupport vector machine regression with Gaussian Kernel functionRidgeRidge regressionLASSOLeast absolute shrinkage and selection operator with BIC for lambdaAdaLASSOAdaptive LASSOENElastic NetAdaENAdaptive ENLSTMLong-short-term memory RNN with 3-hidden layersSgLASSOSparse-group-LASSO-MIDAS with block-K-fold CV for lambda & alphaList of methods for treating mixed-frequenciesAcronymTransformation DescriptionD1Down-sampling to Quarterly (Temporal aggregation with equal-weights)D2Unrestricted MIDAS PolynomialsD3Legendre Polynomials (3rd degree)The Ranking: Real-time model evaluationThe table reports RMSE’s relative to the AR(1) benchmark for the n-quarters ahead prediction, with n=0 reflecting the nowcast. The models have been ranked wrt the last column which corresponds to the average relative RMSE over all 5 horizons. The real-time POOS evaluation is based on 220 monthly vintages over the period Jan-2003 to Apr-2021. D1 denotes single-frequency information set; D2 U-MIDAS polynomials; and D3 Legendre polynomials. The table ranks specifications coming from the different combinations of ML models with all the transformations D1, D2 and D3 plus their factor-only counterparts. Models with an acronym ending in ‘F’ contain only factors on the RHS.Modelsn=0n=1n=2n=3n=4avgBag-D30.7280.9320.9720.9980.9940.925CSR-D20.7070.9380.97611.0040.925BBoost-D1F0.7250.9250.9781.0061.0010.927Bag-D2F0.7720.910.9670.9940.9990.929Ridge-D10.7640.9240.9580.9961.0010.929Ridge-D20.7420.9260.9721.0011.0050.929Bag-D20.7670.9210.9690.9931.0020.93T.ARDI(2)0.7450.9290.9751.0021.0070.932Bag-D1F0.7590.9250.971.0051.0010.932Bag-D10.7830.9180.9610.9961.0020.932CSR-D10.7580.9340.9741.0041.0090.936Ridge-D30.7910.9210.9691.0041.0030.938RF-D1F0.8160.9170.9660.9950.9920.938Ridge-D2F0.8080.9130.9680.9991.0040.938CBoost-D1F0.7730.9250.9831.011.0010.938SVR-D10.8250.9190.9640.9920.9950.939LASSO-D1F0.7870.930.9781.0020.9990.939AdaLASSO-D1F0.7810.9370.981.0030.9980.94RF-D10.8040.9240.9710.9991.0030.94Bag-D3F0.8160.9170.9721.0050.9930.941EN-D2F0.8160.9210.9690.9991.0010.941EN-D1F0.7990.9280.9781.00110.941SVR-D30.8270.920.970.9950.9970.942RF-D30.8120.9360.9690.9941.0010.942ARDI(1)0.7990.9390.9750.9991.0010.943CBoost-D2F0.8210.920.9650.9991.0080.943BBoost-D2F0.8360.9120.9670.99810.943SVR-D3F0.8310.9140.9720.9951.0010.943SVR-D20.8280.9230.9710.9970.9970.943AdaEN-D20.7660.9470.9771.0031.0240.943EN-D20.7770.9710.9780.9960.9940.943RF-D20.8160.9250.9761.00110.943LASSO-D2F0.8310.920.9690.99810.944AdaEN-D1F0.8020.9340.9811.00210.944SVR-D1F0.8270.9210.9710.99910.944CSR-D2F0.8240.9280.970.99710.944SVR-D2F0.8310.9250.9720.9960.9950.944RF-D2F0.8270.9290.9720.9980.9950.944BTree-D1F0.8110.9230.9751.0021.0080.944AdaEN-D2F0.8340.9260.9650.9991.0020.945AdaLASSO-D2F0.840.9220.9660.9981.0010.945AdaLASSO-D20.7650.9540.9790.9981.0340.946LSTM-D1F0.8450.9180.9681.0050.9940.946ARDI(2)0.7980.9470.9781.0011.0080.946EN-D30.8340.9240.975110.947CSR-D30.8140.9310.981.0051.0030.947RW0.8390.9210.9750.9990.9990.947LSTM-D2F0.8440.9280.96610.9970.947LASSO-D20.780.980.98310.9970.948BVAR-CSV0.8110.9260.981.0121.0130.948RF-D3F0.8440.9340.9760.9911.0010.949T.ARDI(1)0.8140.9480.9751.0051.0070.95AdaEN-D10.8170.9310.9911.0071.0030.95BBoost-D3F0.8650.9060.9731.0061.0010.95AdaEN-D30.8480.9280.97611.0020.951LSTM-D3F0.8510.9260.9720.9941.0130.951SgLASSO-D30.8490.9250.9781.0031.0050.952SgLASSO-D3F0.8610.9120.9771.0111.0030.953CSR-D1F0.8770.9250.970.9980.9990.954EN-D10.8090.9360.9441.0451.0360.954BTree-D10.8120.9330.9881.0151.0240.955AdaEN-D3F0.8830.9240.9681.0010.9990.955LSTM-D30.8580.9320.9781.0051.0040.955BVAR-Minn0.850.9330.9741.0121.0150.957EN-D3F0.8910.9260.97110.9990.957CBoost-D3F0.8540.9360.9851.0131.0010.958LSTM-D10.8660.9360.9781.0021.0130.959CSR-D3F0.890.9380.971.0010.9970.959LASSO-D3F0.9030.9210.97111.0030.96AdaLASSO-D3F0.8930.9290.9711.0031.0040.96BTree-D2F0.850.9540.9911.0170.9970.962LSTM-D20.8680.9430.9861.0170.9990.962BTree-D20.8390.9520.9941.0121.0160.963Ridge-D3F0.8020.9411.0171.0461.0330.968AdaLASSO-D10.830.9471.0191.0371.0220.971BTree-D30.8510.9880.991.0161.0210.973Ridge-D1F0.7790.9591.0261.061.0540.976LASSO-D30.8320.9321.0181.061.0560.98AdaLASSO-D30.8340.9451.031.0651.060.987LASSO-D10.7741.0070.9871.1021.0740.989BTree-D3F0.881.0310.9991.011.0330.991AR(BIC)1.0081.00311.00111.002AR(CV)1.021.00411.0010.9991.005AR(4)1.0491.0171.0020.9990.9991.013AR(1)NaNNaNNaNNaNNaNNaNThe graph provides a visualization of the horse race. Furthermore, it adds a second crucial metric for measuring comparative performance, the MAE. The axes show the relative error measures (RMSE and MAE) averaged over all 5 horizons. Candidate models that are closest to the origin (-bottom left) are the best performers. You might also find the Plotly JSON Editor useful.MathWowchemy supports a Markdown extension for $\LaTeX$ math. You can enable this feature by toggling the math option in your config/_default/params.yaml file.To render inline or block math, wrap your LaTeX math with {{< math >}}$...${{< /math >}} or {{< math >}}$$...$${{< /math >}}, respectively. (We wrap the LaTeX math in the Wowchemy math shortcode to prevent Hugo rendering our math as Markdown. The math shortcode is new in v5.5-dev.)Example math block:{{< math >}} + - Math: $x = {-b \pm \sqrt{b^2-4ac} \over 2a}$ChartsWowchemy supports the popular Plotly format for interactive charts.Save your Plotly JSON in your page folder, for example line-chart.json, and then add the {{< chart data="line-chart" >}} shortcode where you would like the chart to appear.Demo:You might also find the Plotly JSON Editor useful.MathWowchemy supports a Markdown extension for $\LaTeX$ math. You can enable this feature by toggling the math option in your config/_default/params.yaml file.To render inline or block math, wrap your LaTeX math with {{< math >}}$...${{< /math >}} or {{< math >}}$$...$${{< /math >}}, respectively. (We wrap the LaTeX math in the Wowchemy math shortcode to prevent Hugo rendering our math as Markdown. The math shortcode is new in v5.5-dev.)Example math block:{{< math >}} $$ \gamma_{n} = \frac{ \left | \left (\mathbf x_{n} - \mathbf x_{n-1} \right )^T \left [\nabla F (\mathbf x_{n}) - \nabla F (\mathbf x_{n-1}) \right ] \right |}{\left \|\nabla F(\mathbf{x}_{n}) - \nabla F(\mathbf{x}_{n-1}) \right \|^2} $$
The Big Macro Nowcasting RankingThe objective of this page is to maintain and populate the ranking below, with newly introduced statistical models in an effort to provide a continuously updated comprehensive comparison of methodologies for nowcasting and forecasting macroeconomic activity. The model comparison is based on a set of (pseudo) real-time vintages, formed using a rich standardized set of variables at mixed-frequencies.The performance evaluation currently covers US real GDP growth rate (QoQ%), comparing 20 distinct methodologies (including ML, as well as standard econometric techniques and workhorse benchmarks), which are combined with three data transformations (D1,D2,D3) for taking into account the mixed-frequency dimension. This results into a ranking containing a total of 85 specifications.The dataset consists of 87 quarterly, and 171 monthly (including 31 financial market) indicators. The indicators correspond to the series found in the FRED-MD and -QD datasets and were downloaded at their original (i.e. highest-available) sampling frequency, whenever possible. Publication release delays were inferred from the metadata in the FRED database (https://fred.stlouisfed.org) and then applied to each series to mimic the ragged-edge structure the forecaster would face in reality. The out-of-sample evaluation uses end-of-month vintages at a monthly periodicity, assuming that economic activity is monitored in \textit{real-time} by updating the projections at the end of every month.A list of the indicators that compose the mixed-frequency dataset, can be accessed +here. +SeriesID refers to the FRED mnemonic, while the release delay (RDelay) measures the approximate number of days it takes for the respective indicator to be released after the closing of the reference month or quarter. The monthly mixed-frequency vintages used in the POOS model evaluation can be downloaded here. The full set consists of 376 end-of-month vintages spanning the period 19900131-20210430, including monthly and quarterly unbalanced panels whose ragged edge has been imposed by applying the inferred publication delays.List of forecasting modelsAcronymModel DescriptionAR(P)Autoregressive iterated-specificationRWRandom walkARDI(K,BIC)Autoregressive diffusion indices with K factors. Optimal lag-order via BICT.ARDI(K,BIC)ARDI with target-factors. Hard-threshold set to |t-stat|>1.96BVAR-MinnHomoscedastic large Bayesian VARBVAR-CSVLarge Bayesian VAR with heteroscedastic innovationsBBoostQuadratic-loss L2 boosting, block-wiseCBoostQuadratic-loss L2 boosting, component-wiseCSRComplete Subset Regressions (20C4) with hard-thresholding preselectionBagLinear bagging with hard-thresholding preselectionBTreeBoosting regression treesRFRandom forestsSVRSupport vector machine regression with Gaussian Kernel functionRidgeRidge regressionLASSOLeast absolute shrinkage and selection operator with BIC for lambdaAdaLASSOAdaptive LASSOENElastic NetAdaENAdaptive ENLSTMLong-short-term memory RNN with 3-hidden layersSgLASSOSparse-group-LASSO-MIDAS with block-K-fold CV for lambda & alphaList of methods for treating mixed-frequenciesAcronymTransformation DescriptionD1Down-sampling to Quarterly (Temporal aggregation with equal-weights)D2Unrestricted MIDAS PolynomialsD3Legendre Polynomials (3rd degree)The Ranking: Real-time model evaluationThe table reports RMSE’s relative to the AR(1) benchmark for the n-quarters ahead prediction, with n=0 reflecting the nowcast. The models have been ranked wrt the last column which corresponds to the average relative RMSE over all 5 horizons. The real-time POOS evaluation is based on 220 monthly vintages over the period Jan-2003 to Apr-2021. D1 denotes single-frequency information set; D2 U-MIDAS polynomials; and D3 Legendre polynomials. The table ranks specifications coming from the different combinations of ML models with all the transformations D1, D2 and D3 plus their factor-only counterparts. Models with an acronym ending in ‘F’ contain only factors on the RHS.Modelsn=0n=1n=2n=3n=4avgBag-D30.7280.9320.9720.9980.9940.925CSR-D20.7070.9380.97611.0040.925BBoost-D1F0.7250.9250.9781.0061.0010.927Bag-D2F0.7720.910.9670.9940.9990.929Ridge-D10.7640.9240.9580.9961.0010.929Ridge-D20.7420.9260.9721.0011.0050.929Bag-D20.7670.9210.9690.9931.0020.93T.ARDI(2)0.7450.9290.9751.0021.0070.932Bag-D1F0.7590.9250.971.0051.0010.932Bag-D10.7830.9180.9610.9961.0020.932CSR-D10.7580.9340.9741.0041.0090.936Ridge-D30.7910.9210.9691.0041.0030.938RF-D1F0.8160.9170.9660.9950.9920.938Ridge-D2F0.8080.9130.9680.9991.0040.938CBoost-D1F0.7730.9250.9831.011.0010.938SVR-D10.8250.9190.9640.9920.9950.939LASSO-D1F0.7870.930.9781.0020.9990.939AdaLASSO-D1F0.7810.9370.981.0030.9980.94RF-D10.8040.9240.9710.9991.0030.94Bag-D3F0.8160.9170.9721.0050.9930.941EN-D2F0.8160.9210.9690.9991.0010.941EN-D1F0.7990.9280.9781.00110.941SVR-D30.8270.920.970.9950.9970.942RF-D30.8120.9360.9690.9941.0010.942ARDI(1)0.7990.9390.9750.9991.0010.943CBoost-D2F0.8210.920.9650.9991.0080.943BBoost-D2F0.8360.9120.9670.99810.943SVR-D3F0.8310.9140.9720.9951.0010.943SVR-D20.8280.9230.9710.9970.9970.943AdaEN-D20.7660.9470.9771.0031.0240.943EN-D20.7770.9710.9780.9960.9940.943RF-D20.8160.9250.9761.00110.943LASSO-D2F0.8310.920.9690.99810.944AdaEN-D1F0.8020.9340.9811.00210.944SVR-D1F0.8270.9210.9710.99910.944CSR-D2F0.8240.9280.970.99710.944SVR-D2F0.8310.9250.9720.9960.9950.944RF-D2F0.8270.9290.9720.9980.9950.944BTree-D1F0.8110.9230.9751.0021.0080.944AdaEN-D2F0.8340.9260.9650.9991.0020.945AdaLASSO-D2F0.840.9220.9660.9981.0010.945AdaLASSO-D20.7650.9540.9790.9981.0340.946LSTM-D1F0.8450.9180.9681.0050.9940.946ARDI(2)0.7980.9470.9781.0011.0080.946EN-D30.8340.9240.975110.947CSR-D30.8140.9310.981.0051.0030.947RW0.8390.9210.9750.9990.9990.947LSTM-D2F0.8440.9280.96610.9970.947LASSO-D20.780.980.98310.9970.948BVAR-CSV0.8110.9260.981.0121.0130.948RF-D3F0.8440.9340.9760.9911.0010.949T.ARDI(1)0.8140.9480.9751.0051.0070.95AdaEN-D10.8170.9310.9911.0071.0030.95BBoost-D3F0.8650.9060.9731.0061.0010.95AdaEN-D30.8480.9280.97611.0020.951LSTM-D3F0.8510.9260.9720.9941.0130.951SgLASSO-D30.8490.9250.9781.0031.0050.952SgLASSO-D3F0.8610.9120.9771.0111.0030.953CSR-D1F0.8770.9250.970.9980.9990.954EN-D10.8090.9360.9441.0451.0360.954BTree-D10.8120.9330.9881.0151.0240.955AdaEN-D3F0.8830.9240.9681.0010.9990.955LSTM-D30.8580.9320.9781.0051.0040.955BVAR-Minn0.850.9330.9741.0121.0150.957EN-D3F0.8910.9260.97110.9990.957CBoost-D3F0.8540.9360.9851.0131.0010.958LSTM-D10.8660.9360.9781.0021.0130.959CSR-D3F0.890.9380.971.0010.9970.959LASSO-D3F0.9030.9210.97111.0030.96AdaLASSO-D3F0.8930.9290.9711.0031.0040.96BTree-D2F0.850.9540.9911.0170.9970.962LSTM-D20.8680.9430.9861.0170.9990.962BTree-D20.8390.9520.9941.0121.0160.963Ridge-D3F0.8020.9411.0171.0461.0330.968AdaLASSO-D10.830.9471.0191.0371.0220.971BTree-D30.8510.9880.991.0161.0210.973Ridge-D1F0.7790.9591.0261.061.0540.976LASSO-D30.8320.9321.0181.061.0560.98AdaLASSO-D30.8340.9451.031.0651.060.987LASSO-D10.7741.0070.9871.1021.0740.989BTree-D3F0.881.0310.9991.011.0330.991AR(BIC)1.0081.00311.00111.002AR(CV)1.021.00411.0010.9991.005AR(4)1.0491.0171.0020.9990.9991.013AR(1)NaNNaNNaNNaNNaNNaNThe graph provides a visualization of the horse race. Furthermore, it adds a second crucial metric for measuring comparative performance, the MAE. The axes show the relative error measures (RMSE and MAE) averaged over all 5 horizons. Candidate models that are closest to the origin (-bottom left) are the best performers.