Prediction doesn't align with last row

[Tomydispik]

So I pulled this down to work it through with your video and the predictions are coming from the middle of my csv. For instance, I have an AUD/USD df that is about 418 rows long post cleaning. I run through all the steps, dealt with the overfitting based on your suggestions. Then I added a table to print out the last 20 close values along with the predictions and graphs. When I do that I get a last close value that when I look it up it is in line 131 of the csv, has a value of 0.68362. The very last entry in my civ has a value of 0.65876. The prediction and value it is based off is not even close.

Any suggestions on how to fix this?

[mohammad95labbaf]

It seems like the issue might be related to how the data is being processed or indexed. Here are a few suggestions:

1. Check the data slicing: Ensure that the data slicing for training and testing is done correctly. The issue might be due to an incorrect slice of the data for prediction.

2. Inspect the data preprocessing steps: Make sure that any preprocessing steps (like scaling or normalization) are being applied consistently across your training and testing data.

3. Review the model's input: Verify that the model is receiving the correct rows for prediction. It might be worthwhile to print out the inputs to the model during the prediction step to confirm this.

4. Look at the CSV read operation: Sometimes, pandas can interpret the index column incorrectly, especially if the CSV contains an unnamed index column. You might want to check how the CSV is being read into the DataFrame.

5. Dataset Size and Quality: Deep learning models require a large amount of data for effective training. A small dataset might not capture the underlying patterns, leading to inaccurate predictions. If your dataset is small (e.g., only a few hundred rows), it might be insufficient for a deep learning model. Consider collecting more data or using data augmentation techniques to increase your training set size..

Remember, it’s important to thoroughly debug each step to isolate the issue. I hope this helps, and let me know if you have any other questions!