For Traders
Click the green button to start
performing no-code quant
analysis on this security
Backtest DBC
14
The datasets from which these PYPL forecasts are drawn originate from FactSet. They represent the aggregated estimates made available to academics or practitioners via the Institutional Brokers’ Estimate System (IBES). Although this seems like a fair way of predicting future profits given that they have some level expertise in investment banking, studies show there's still an optimism bias present among these professionals.

Regression-based models suffer from the use of past earnings in a linear or exponential framework. This can lead to bias because these models assume that future performance will mirror historical trends exactly, whereas business cycle dynamics and seasonality may introduce randomness over time periods.

While there is a clear consensus that a factor-based approach to investment is rewarded over time, it goes without saying that the implementation of factor investing strategies, especially in the world of long-only money-management, is rarely subject to the same consensus. Index providers who offer funds that generally contain a small number of stocks in relation to the size and risk level they are designed for, often do so by selecting certain conditions or factors within each company.

For example, some commercial indexes aim at proportionality between price movements and dividends paid out over time while others look exclusively on liquidity considerations alone; yet still more restrict their selection criteria based around corporate governance issues like transparency reports rating various aspects such as soundness levels among others relevant metrics available about any given firm when deciding whether it should be included into an investor’s portfolio.

Invesco DB Commodity Index Tracking Fund x Commodity Correlations

Components
Historical price and correlation data
PYPL forecast 2025 logoPYPL forecast 2025 logo

Seasonality

This multi-factor forecast for Paypal Holdings (PYPL) is based on a weighted average of five factor-dervied forecasts.
Backtest PYPL
PYPL forecast 2025 logo
$
Commodity Pearson Correlations Heat Map

Left-hand side y-axis coordinates represent the 1 to 180-day look back periods for Pearson correlation values.
Right-hand side y=axis coordinates measure the price level of DBC.

Commodity Pearson Correlations

Correlation Interval Previous Year Previous Month Last Value
20-day 0.27827 0.16728 0.37393
40-day 0.24867 0.31853 0.21634
60-day 0.18151 0.26273 0.27614
80-day 0.21582 0.26286 0.24906
100-day 0.22858 0.26722 0.25743
120-day 0.22349 0.24876 0.24154
140-day 0.25731 0.24066 0.23975
160-day 0.30102 0.24326 0.23219
180-day 0.30774 0.23136 0.23523
All Correlation Visualizations
Correlation Interval Last Value
20-day 0.37393
40-day 0.21634
60-day 0.27614
80-day 0.24906
100-day 0.25743
120-day 0.24154
140-day 0.23975
160-day 0.23219
180-day 0.23523

About Heat Map Colors

This average correlation heat map uses a color scheme to represent how strongly the DBA, DBE, DBP and DBB components exhibit a positive (red), somewhat positive (white), or low / inverse average correlation (green). Different shades of these three colors represent the strength or weakness of the average correlation as shown on the heatmap colorbar legend, to the right of the heatmap itself.

About Heat Map Coordinates

The X-axis displays trading days by date, and the Y-axis contains different n-day average correlation look back periods. For example, The 180-day average of Pearson correlation value calculated on a specific date appears on the heat map at the intersection of Y-coordinate "180" and X-coordinate of the specific date.

About Chart Overlay

A price chart of Invesco DB Commodity Index Tracking Fund is overlaid on top of the heat map so you can observe the impact that different average correlation regimes may be having on the price of the asset.

As a general observation, high correlation regimes are accompanied by high volatility in price movements, and vice-versa.

Note that traders who need a perform a more comprehensive analysis can backtest the impact of each of these n-day average correlations using the Tradewell platform.

About Pearson Correlations

The Pearson correlation coefficient is a measure of linear strength between two sets of data. In financial markets is used to determine whether the variability of returns between a group of assets is linearly related.

In the example of this heat map analysis of Invesco DB Commodity Index Tracking Fund, we are measuring the average correlations between the components over various look-back periods, spanning 10 days to 180 days. In the example of this heat map analysis of Invesco DB Commodity Index Tracking Fund, we are measuring the average correlations between the components over various look-back periods, spanning 10 days to 180 days.

A coefficient value of -1 represents a maximally inverse relationship between the variables, whereas a value of 1 represents a maximally positive relationship. A value of 0 indicates no linear relationship between the variables.

For example, a 20-day average correlation value of 1 would indicate that variability of the index components returns has been perfectly linearly related over the previous 20 days.

Invesco DB Commodity Index Tracking Fund

DBC seeks to track changes in the level of DBIQ Optimum Yield's Commodity Index. The fund's portfolio includes: exchange-traded futures on Light Sweet Crude Oil (WTI), Heating Oil, RBOB Gasoline Natural Gas Brent Crude Oil; Gold , Silver, Aluminum, Zinc, Copper (Grade A), Corn, Wheat, Soybeans and Sugar.
All Correlation Visualizations

Correlations

This heat map shows the average Pearson correlation values between DBA, DBE, DBP and DBB over the past year of trading.
Components
Historical price and correlation data
PYPL forecast 2025 logoPYPL forecast 2025 logo
PYPL forecast 2025 logo
AAPL
Guest Commentary
Robson Chow is a hedge fund manager
Trending
Tradewell is not responsible for the content, data, or information on third-party websites or provided by third-party data providers. We publish links to various external sources and data from various data providers as a convenience, but we cannot verify any claims made by those sites and cannot guarantee that they are safe interpretations of information provided within these pages. If you choose to visit a linked site or consume data, you do so at your own risk and you will be subject to such sites' terms of use and privacy policies, over which Tradewell has no control. Tradewell shall not be liable for any damages incurred by visiting the linked sites or by making decisions or interpreting the data published on webpages or in the Tradewell app.

The information contained on this website is current as of the date indicated, and may be superseded by subsequent market events or for other reasons. The views and opinions expressed on this website are those of the authors alone - they do not necessarily reflect those held by Tradwell, its affiliates nor employees alike. Investors should be aware that the information expressed in articles is not intended to relate specifically to any product offered by Tradewell. It's being provided for informational purposes only and cannot serve as investment advice or guidance on your individual financial situation.

Any hypothetical performance shown is based on the retrospective application of a model developed with hindsight. While these results are presented for illustrative purposes only, it's important to note that there may be limitations built into any projection.

Certain articles may have been written prior to the author being an employee or contractor of Tradewell. The views expressed on the website are those of the authors and not necessarily those of Tradewell. Published material is intended for informational purposes only and should not be construed as legal or tax advice, nor is it intended to replace the advice of a qualified attorney or tax advisor.