I would like to forewarn by saying I am by no means an expert in this topic and I apologize if I mix terminology, phrased the question wrong, or any information is incorrect.
I would like to use a machine learning model for the current dataset that I have gathered. The dataset has about 8000 blocks (or entities), and each of these blocks has 7 features. Each feature has around 10 yearly values, which are counts (ex: 2005=1, 2006=2 ... 2014=0, 2015=3). The long stretch goal would be able to predict the 11th, and even 12th, yearly value for each feature.
I would really love to apply machine learning to this dataset. I've looked into the following because they seem to be the best solution to my problem: linear regression models, LSTM neural networks, and time series forecasting, although I am still unsure of how my dataset can fit into these certain models.
Please let me know if I can offer any more information!