1
$\begingroup$

Let's consider we have several hundreds of numbers like ( 1, 2, 5, 8, 7, 15, 19, 8, 4, 6, ...) those are closed numbers of a stock on consecutive days for example. I like to know what algorithms are good to predict next numbers? Is it possible to find a relationship between this sequence of numbers or we need extra input data to make a prediction?

I am completely new on this and seeking some ideas and guidance for a new comer in data science field(although I have some experience in machine learning and image and voice recognition).

$\endgroup$
0
$\begingroup$

Hi this can be approached as a timeseries regression problem. Deep learning (tools like Tensorflow or Keras a higher level API) can be very effective in this. It depends on many factors like the amount and quality of your data, the architecture, the complexity of the problem and hyper parameters whether it will be useful to you. machinelearningmastery.com has many examples of LSTM have a look at it! Maybe start with this. As you can see in the examples in 2 having the numbers you mentioned and the sequence in which they occured could be enough to predict the next number(s). Usually adding more information to your neural network should make it improve.

$\endgroup$
0
$\begingroup$

What is a time series

A time series is a series of data points indexed (or listed or graphed) in time order. Most commonly, a time series is a sequence taken at successive equally spaced points in time. Thus it is a sequence of discrete-time data. Examples of time series are heights of ocean tides, counts of sunspots, and the daily closing value of the Dow Jones Industrial Average.

Time series analysis

Time series analysis has two main objectives:

  • Obtain an understanding of the underlying forces and structure that produced the observed data
  • Fit a model and proceed to forecasting, monitoring or even feedback and feedforward control.

This is the first step on the topic you are looking for.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.