I’m looking to develop a Machine Learning/Deep Learning model to predict whether a stocks current day data is noise or is a signal for Over/Under performance vs a benchmark for the next day. I would like to get Over/Under prediction and a probability of the signal. Should I use LTSM RNN even if the model only takes in todays data to predict tomorrow or is Hidden Markov Model the way to go?

Hi Stackoverflow community,

import numpy as np
#Reference: How to fix ‘Object arrays cannot be loaded when allow_pickle=False’ for imdb.load_data() function?
np_load_old = np.load

Here is the link click

I am building a classification model based on the Kaggle Dataset.

I’m making a model which predicts middle point of the road.
here is what I’m trying to do.

I have Nvidia 1660Ti 6GB, Cuda 11.8, CuDNN 9.1, Win 64 23H2, Anaconda 2.6 . Its been 3 days I have been struggling to install Cuda.
Its generating a lot of error related to PIP, tensorflow is not able to find the GPU. How to install it without any error.

My ANN’s results are completely different, test results can’t go higher than 1 or 2 and my f1-score and accuracy are sometimes even 1. I think there is data leakage and I tried everything I can. I was using ColumnTransformer for y but because on a different forum someone said it might be the problem I changed to pd dummies. How can I solve the issue?