Alpha_2 Discussion - kitzz03/WorldQuant-Alphas GitHub Wiki
Paper
Market participants generally had stronger reactions to the net percentage of upward and downward revisions in earnings estimates rather than the percentage change of the consensus estimate figures - Meaning ??
Earnings revision strategies tended to generate more alpha in the small-cap universe than in the large-mid-cap universe, although there was no strong sector or size bias - Reason ??
Xu found that from 2002 to 2003, earnings revision strategies failed to deliver excess return in the U.S., and this seemed to be caused by market participants’ overreactions as a result of over-extrapolating the success of the strategies in earlier periods. However, he also suggested that earnings estimate revisions continued to be serially correlated and remained a possible source for alpha. Feldman, Livnat, and Zhang examined the market’s reactions to analyst revisions on earnings estimates, target prices, and stock recommendations in the U.S. and found all three revisions were associated with significant positive excess returns. They concluded that the market reacted significantly stronger to target price and stock recommendation revisions than to earnings estimate revisions; however, revisions on target price and stock recommendation were far fewer than revisions on earnings estimates
The top quintile EPS diffusion portfolios delivered significantly higher average monthly excess return over their respective universes in the majority of the markets in comparison to the top quintile EPS change portfolios. This suggested that market participants had stronger reactions to the net percentage of upward and downward revisions in the EPS estimate rather than the percentage change of the consensus earnings estimate figures.
Companies with poor earnings revisions tended to have more volatile returns, as market participants reacted negatively to companies with downward revisions in estimates. We also noticed that market participants tended to penalize stocks with poor earnings revisions more when the market was in a downward trend.
https://www.investopedia.com/articles/stocks/06/earningsforecasts.asp
https://corporatefinanceinstitute.com/resources/valuation/what-is-beta-guide/
Alpha
a = vector_neut((rank(mdl175_darev)),(1+rank(mdl175_moneyflow20)))*(1+rank(mdl175_beta20));
group = bucket(rank(cap) , range = '0,1,0.25');
c = group_neutralize(a,group);
d = ts_decay_exp_window(c,10, factor = 0.2); d
Hypothesis
Stocks with upwards earnings revision by analysts and high beta values can be seen as undervalued growth opportunities that can lead amplified returns during market upswings.
(Analysts may revise earnings estimates to reflect the changes in the expectations of the company’s performance in the future. This tends to occur following a better or worse than expected profit announcement or changes in the economic conditions. Their recommendations can significantly affect share prices, with upgrades to EPS forecasts capable of pushing share prices higher. The change to earnings forecasts is known as earnings revision.)
(“Do Earnings Revisions Matter in Asia” by S&P Global in December 2017 revealed that stock prices tend to move in the same direction as their earnings revisions in the majority of the Pan Asian markets)
(Earnings forecasts are based on analysts' expectations of company growth and profitability. To predict earnings, most analysts build financial models that estimate prospective revenues and costs.
Many analysts will incorporate top-down factors such as economic growth rates, currencies and other macroeconomic factors that influence corporate growth. They use market research reports to get a sense of underlying growth trends. To understand the dynamics of the individual companies they cover, really good analysts will speak to customers, suppliers and competitors. The companies themselves offer earnings guidance that analysts build into the models.
To predict revenues, analysts estimate sales volume growth and estimate the prices companies can charge for the products. On the cost side, analysts look at expected changes in the costs of running the business. Costs include wages, materials used in production, marketing and sales costs, interest on loans, etc.
Analysts' forecasts are critical because they contribute to investors' valuation models. Institutional investors, who can move markets due to the volume of assets they manage, follow analysts at big brokerage houses to varying degrees.)
Datasets used:
mdl175_darev: Changes of forecast earnings by analyst
The basic measurement of earnings is earnings per share. This metric is calculated as the company's net earnings—or net income found on its income statement—minus dividends on preferred stock, divided by the number of outstanding shares)
(So, why does the investment community focus on earnings, rather than other metrics such as sales or cash flow? Any finance professor will tell you the only proper way to value a stock is to predict the long-term free cash flows of a company, discount those free cash flows to the present day and divide by the number of shares. But this is much easier said than done, so investors often shortcut the process by using accounting earnings as a "good enough" substitute for free cash flow. Accounting earnings certainly are a much better proxy for free cash flow than sales. Besides, accounting earnings are fairly well defined and public companies' earnings statements must go through rigorous accounting audits before they are released. As a result, the investment community views earnings as a fairly reliable, not to mention convenient, measure. (To read more, see: Getting The Real Earnings.)
https://www.investopedia.com/terms/f/freecashflow.asp https://www.investopedia.com/terms/d/dcf.asp#:~:text=Discounted%20cash%20flow%20(DCF)%20refers,will%20generate%20in%20the%20future. https://www.investopedia.com/ask/answers/111714/what-are-some-examples-how-cash-flows-can-be-manipulated-or-distorted.asp#:~:text=Changing%20Accounts%20Payable&text=Another%20technique%20that%20a%20company,larger%20than%20it%20otherwise%20should.
For example, assume that a company made $50,000,000 per year in net income each year for the last decade. On the surface, that seems stable. But what if FCF was dropping over the last two years as inventories were rising (outflow), customers started to delay payments (inflow), and vendors began demanding faster payments (outflow)? In this situation, FCF would reveal a serious financial weakness that wouldn’t be apparent from an examination of the income statement.
mdl175_moneyflow20: 20-day money flow (Money flow is calculated by averaging the high, low and closing prices, and multiplying by the daily volume. Comparing that result with the number for the previous day tells traders whether money flow was positive or negative for the current day. Positive money flow indicates that prices are likely to move higher, while negative money flow suggests prices are about to fall.)
mdl175_beta20: 20-day Beta value of individual stocks
Initial Alpha
With some explanation about sharpe/ turnover/ returns-to-drawdown ratio
Some explanation of why such a setting is choosen
possible explanation of areas where alpha has huge drawdown/ profit (jump)/ or is stagnant (no profit or loss for a large period)
[what was happening to the US/CHN market at that time]
image of initial pnl
Improved Alpha
explanation why such strategies are used
improvement can be in multiple steps with pnl of each step attached
Answers to questions by judges:
possible questions with answers which can be expected from the judges
if you dont find answer to a specific question add the question and leave it blank, we will discuss together. 1 2 3 4
Links:
links to sources research papers articles news etc.
Backstory:
(optional)
some quote
something related to chess
some book
Further scope of improvement:
(Consensus estimates are so powerful that even small deviations can send a stock higher or lower. If a company exceeds its consensus estimates, it is usually rewarded with an increase in stock price. If a company falls short of consensus numbers—or sometimes if it only meets expectations—its share price can take a hit.
With so many investors watching consensus numbers, the difference between actual and consensus earnings is perhaps the single most important factor driving share-price performance over the short term.)
group_zscore: the alpha to reduce weight concentration i.e, remove outliers
ChatGPT:
Reasons for Neutralizing with Respect to Money Flow Controlling for Investor Sentiment:
Money Flow as Sentiment Indicator:
Definition: Money flow measures the net inflow and outflow of money into a stock over a given period. It reflects the aggregate buying and selling activities of investors. Indication of Interest: High money flow is a signal of strong investor interest, indicating that a stock is being actively accumulated or distributed by investors. Sources: Money flow is often used in technical analysis to gauge investor sentiment and market trends . Impact on Price:
Market Movements: Stocks with high money flow are likely experiencing significant price movements driven by investor actions, such as heavy buying or selling. Potential Distortion: These price movements may not necessarily reflect changes in the stock's intrinsic value but rather short-term investor behavior and sentiment . Isolating Revisions Impact:
Goal: By neutralizing earnings revisions with respect to money flow, the alpha signal aims to isolate the specific effect of changes in earnings expectations. Avoiding Confounding Effects: This ensures that the signal primarily captures the impact of earnings revisions rather than being distorted by the broader investor/institutional trader sentiment and market dynamics . Reasons for Neutralizing with Respect to Beta Controlling for Market Sensitivity:
Beta as Volatility Measure:
Definition: Beta is a measure of a stock's volatility relative to the overall market. A beta greater than 1 indicates that the stock is more volatile than the market, while a beta less than 1 indicates lower volatility. Sensitivity to Market Movements: High-beta stocks tend to amplify market movements, showing greater increases in up markets and larger decreases in down markets . Impact on Returns:
Higher Returns and Risks: Stocks with high beta values may exhibit higher returns during market upswings but also carry higher risks during downturns. Volatility Influence: The performance of high-beta stocks is heavily influenced by overall market movements, which can overshadow the effects of other factors like earnings revisions . Isolating Revisions Impact:
Goal: By neutralizing earnings revisions with respect to beta, the alpha signal seeks to ensure that the predictive power of earnings revisions is not confounded by the stock's inherent volatility. Clearer Signal: This helps in capturing the true impact of earnings revisions on stock performance, independent of the systematic risk captured by beta . Summary Neutralizing earnings revisions with respect to both money flow and beta helps in isolating the specific impact of earnings revisions on stock performance. This approach controls for the influences of investor sentiment and market sensitivity, leading to a more robust and reliable alpha signal for identifying potential growth opportunities.
Sources Investopedia - Money Flow Definition: https://www.investopedia.com/terms/m/moneyflow.asp Investopedia - Understanding Money Flow Index: https://www.investopedia.com/terms/m/mfi.asp CFA Institute - Market Sentiment Indicators: https://www.cfainstitute.org/en/research/financial-analyst-journal/2020/market-sentiment-indicators Wiley Online Library - Investor Sentiment and Stock Market Response: https://onlinelibrary.wiley.com/doi/full/10.1111/j.1540-6261.2005.00747.x SSRN - Investor Sentiment and Stock Prices: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2510645 ResearchGate - The Impact of Investor Sentiment on Stock Returns: https://www.researchgate.net/publication/343601348 Investopedia - Beta Definition: https://www.investopedia.com/terms/b/beta.asp Investopedia - Beta and Its Importance in Stock Valuation: https://www.investopedia.com/terms/b/beta.asp CFA Institute - The Role of Beta in Portfolio Management: https://www.cfainstitute.org/en/research/financial-analyst-journal/2020/the-role-of-beta-in-portfolio-management Wiley Online Library - Beta, Risk, and Return: https://onlinelibrary.wiley.com/doi/full/10.1111/j.1540-6261.1980.tb04316.x SSRN - The Impact of Volatility on Stock Returns: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2800973 ResearchGate - Beta and the Cross-Section of Stock Returns: https://www.researchgate.net/publication/220503295
The performance difference of an alpha signal in delay-0 versus delay-1 settings can be attributed to the immediacy and timeliness of the information it uses. Here’s a detailed explanation:
Alpha Signal Definition and Delays Delay-0 Setting:
Definition: The alpha signal uses information available up to the current time (t) to make trading decisions. There is no lag between the observation of the signal and the execution of the trade. Immediacy: This allows the model to react immediately to new information, capturing any immediate price movements or market reactions to changes in earnings revisions, money flow, or beta. Delay-1 Setting:
Definition: The alpha signal uses information up to the previous time period (t-1) to make trading decisions. There is a one-period lag between the observation of the signal and the execution of the trade. Lag: This introduces a delay in responding to new information, which may result in missed opportunities or less optimal trade executions as the market may have already adjusted to the information. Reasons for Better Performance in Delay-0 Settings Timeliness of Information:
Immediate Reaction: In a delay-0 setting, the alpha signal can immediately respond to new earnings revisions, changes in money flow, and fluctuations in beta. This allows for the capture of immediate market reactions and short-term price movements. Real-Time Adjustments: The ability to make real-time adjustments ensures that the model can take advantage of transient opportunities that may quickly dissipate. Market Efficiency:
Information Absorption: Financial markets are generally efficient at absorbing and reflecting new information. In a delay-1 setting, by the time the alpha signal reacts, the information might already be priced in, reducing the potential for generating excess returns. Lag Impact: The one-period lag can result in the alpha signal reacting to outdated information, leading to suboptimal trading decisions and missed profit opportunities. Short-Term Predictive Power:
High-Frequency Signals: Alpha signals that rely on short-term changes, such as earnings revisions and money flow, tend to have high predictive power in the very short term. A delay-0 setting leverages this short-term predictive power effectively. Decay of Signal: The predictive power of such signals can decay quickly over time. A delay-1 setting may capture a weaker signal, as the immediate impact of the information may have already played out. Market Dynamics:
High Volatility Periods: During periods of high market volatility, the ability to react immediately to new information is crucial. Delay-0 settings provide a competitive edge in such environments by allowing the model to capitalize on rapid market movements. Opportunistic Trading: Delay-0 settings enable more opportunistic trading, taking advantage of brief windows where the market has not yet fully adjusted to new information. Example Scenario Earnings Revision Announcement: Delay-0: An earnings revision is announced, indicating a significant upward revision in forecast earnings. The alpha signal in a delay-0 setting can immediately capture this information and execute trades to capitalize on the expected positive price movement. Delay-1: In a delay-1 setting, the same earnings revision is observed one period later. By then, the market may have already adjusted to the new information, and the stock price may have already moved, reducing the potential for excess returns. Summary The better performance of the alpha in delay-0 settings compared to delay-1 can be attributed to the immediacy and timeliness of information usage, allowing the model to react swiftly to new information and capture short-term market inefficiencies. The delay-1 setting introduces a lag that can result in missed opportunities and less optimal trading decisions, as the market may have already absorbed and reflected the new information by the time the trades are executed.
CAPM
https://www.investopedia.com/terms/c/capm.asp
The capital asset pricing model, or CAPM, is a financial model that calculates the expected rate of return for an asset or investment.
CAPM does this by using the expected return on both the market and a risk-free asset, and the asset’s correlation or sensitivity to the market (beta).
The CAPM seeks to gauge whether a stock's current price is consistent with its likely return.