Member-only story

prediction problem solved by continuous price and direction of price movement

Natural Gas Price Prediction using Neural Network & Classification Use Cases

Time-Series Analysis with Regression & Classification use cases

Sarit Maitra
Towards Data Science
9 min readOct 29, 2019

--

Image by author

https://sarit-maitra.medium.com/membership

FORECASTING time-series is a difficult task especially when we are dealing with stochastic price series of stock data. Well, here stochastic means chaotic in true sense clubbed with non-stationarity. Moreover, because of the complexity of stock data, development of efficient models for predicting is very difficult. However, returns do exhibit some kind of predictability and application of modern ML techniques, effective feature engineering helps might be able to push the limits of predicting stock returns.

Here, I will use machine learning algorithms to train my machine on historical price records and predict the expected future price. Let’s see how accurately our algorithms can predict. I will use regression use case and solve the problem by implementing LSTM; subsequently, will use classification use case to solve the problem by applying various classification algorithms.

--

--

Towards Data Science
Towards Data Science

Published in Towards Data Science

Your home for data science and AI. The world’s leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals.

Sarit Maitra
Sarit Maitra

Written by Sarit Maitra

Analytics & Data Science Practice Lead

Responses (12)