Usage

Enter apple or AAPL to search

Use ; to split multiple search items

Leave blank and press "Run" to go Home

6m ahead

Portfolio

Predictive Factors

The models identify what we call the causally predictive factors: a small set of assets judged to be the most important driving forces behind your selected item's forecast. These are what we believe are pushing the search target(s).

Marriott International Class A Common Stock

iShares 1-3 Year Treasury Bond ETF

Microsoft

China / U.S. Foreign Exchange Rate USDCNY

SPDR S&P Dividend ETF

as of

Our Probabilistic Prediction

With the predictive features above, we run many models repeatedly and aggregate them to account for randomness introduced at the training start.

2024-04-25T23:20:33.884307 image/svg+xml Matplotlib v3.7.3, https://matplotlib.org/
2024-04-25T23:20:35.419789 image/svg+xml Matplotlib v3.7.3, https://matplotlib.org/
2024-04-25T23:20:36.483288 image/svg+xml Matplotlib v3.7.3, https://matplotlib.org/
Goodness of Probabilistic Prediction

When prediction is done well, the realised probability level should not be concentrated particularly around anywhere but uniformly between 0 and 1 (whitepaper). We draw a sample of the realised probability levels and check its empirical probability density. The dotted line for that of the uniform distribution.

Under the hypothesis the realised probability level follow the ideal uniform distribution, a p-value can be calculated for the chance (0 to 1) of obtaining this sample. A smaller p-value for a slimmer chance. Below uses significance level 0.001 as cut-off on the p-value. The user is free to use another e.g. 0.01, 0.05 for the test of goodness.

Invesco Nasdaq-100 ETF

🔴 p-value: 0.0 < 0.001

2024-04-25T23:20:34.260784 image/svg+xml Matplotlib v3.7.3, https://matplotlib.org/

SPDR S&P 500 ETF

🔴 p-value: 0.0 < 0.001

2024-04-25T23:20:35.781730 image/svg+xml Matplotlib v3.7.3, https://matplotlib.org/

SPDR Dow Jones Industrial Average ETF

🟢 p-value: 0.011 > 0.001

2024-04-25T23:20:36.874109 image/svg+xml Matplotlib v3.7.3, https://matplotlib.org/

Which direction do the bulk of the models think movement will shift towards? With each model casting a vote on the likely change, and following an averaging procedure of most recent net predictions, expected future positions are for the upcoming day

% Up % Down % Un­de­cided
Invesco Nasdaq-100 ETF 54% 4% 42%
SPDR S&P 500 ETF 89% 1% 10%
SPDR Dow Jones Industrial Average ETF 98% 1% 0%
Changes are with respect to the following time points:
Time Value
Invesco Nasdaq-100 ETF Wed 24 Apr 426.51
SPDR S&P 500 ETF Wed 24 Apr 505.41
SPDR Dow Jones Industrial Average ETF Wed 24 Apr 384.44