EUR/USD is now exiting it's most seasonally unfavorable period of the year.

This project is done. My seasonality charts are now running on the cloud, and the framework is in place to add more. Technically I made a website, but it currently has no domain since I don't intend to share anything on there.

Historically, this has been a volatile time of the year for NZD/USD. There may be some seasonal strength near term. image

We're going into a historically weak period for USD/CAD. image

Historically, USD/CHF has done very well going into this time of the year. image

Here's my seasonal chart, updated for September, if anyone is interested. image It looks like a good month, followed by a rough October.

I've been quieter than usual lately so I thought I'd provide an update... I've come to find manually running a lot of these scripts takes too long and it's inefficient. Therefore, I decided to move some of my scripts to the cloud where my charts ...

CPI... Same models as last time so they're low confidence, but I'd like to document how they do none-the-less. M/M - Matches expectations. image Y/Y - Below expectations. image

I was just looking at some seasonal charts and noticed GBP/USD has a strong downward bias in August. Thought you all might be interested to see! image

My shot in the dark NFP prediction this month: image All models suggest a much better number than the 205k forecast.

Yes, it could definitely be improved. It hasn't been tuned yet and the data preprocessing may be able to be improved. Those should improve the results by themselves. Then I could always add more/better features, which could make a big difference. ...

I applaud you for reviewing Advances in Financial Machine Learning. It's going to be helpful to ordinary traders through Chapter 3 at least. In particular, I thought it was very interesting to see the types of financial data he likes and what he ...

Welcome aboard Fx3423454, I'm glad to have you join us! You said you're using statistical based strategies, what are you using to do you analysis? (ie Python, Excel, R, C#) There's nothing wrong with equities, plenty of money to be made there too! ...

I don't use MAPE, but here are the mean and median absolute errors along with the R2 for the test set: image For what it's worth, this isn't the top performing model for the test set.

Nope, I've stuck with linear regression and classification based machine learning. Are you using them in Python? Feel free to DM or comment in my journal.

ISM Manufacturing PMI is due tomorrow and the FF forecast is for 46.9. My machine learning models suggest slightly better, with a median forecast of 47.5. image

ISM PMI is due tomorrow and the FF forecast is for 46.0. Here's what my ML models are forecasting. This time I added in the FF forecast as a feature. image And here are the old models without the FF forecast. Some actually have better error ...

It looks like it on their site, but it won't download. I think its something specific to forex because stock tickers work...In any event, AlphaVantage worked so I've got the data I need.

Stooq didn't appear to offer historical forex data, despite having it on their website and offering a ton of other historical data... I winded up using AlphaVantage, which daily data roughly matches ForexFactory's.

Yep, it looks like I'll need to find a new data source. Yahoo! Finance has been convenient to use, but I see they've got some big gaps between their open and close which shouldn't happen during the week: image Moreover, I can't figure out when ...