Questions tagged [forecasting]

The tag has no usage guidance.

75 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
4
votes
2answers
321 views

Time series forecasting dilemma. Could feature engineering overcome time dependency?

I keep reading articles about time series forecasting. They all start from the same assumption: time series forecasting can't be treated as a regression/classification problem. It is time dependent, ...
4
votes
2answers
966 views

Forecasting Multiple (few hundreds) uni-variate time series with inflated zeros

Hello Practitioners, Being a newbie seeking help to gain experience in Data Science. Lets take a scenario where a big company wants to forecast its sales(a specific product) across different ...
3
votes
1answer
82 views

Is an Arma model equivalent to a 1-layer Recurrent Neural Network without activation function?

Given a time series $f(t)$ to forecast, let us consider an Arma model of the form: $$ f(t) = c + \sum_{i=1}^p a_i f(t-i) + e(t) + \sum_{j=1}^q b_j e(t-j) $$ where $e(t)$ are the forecast errors. On ...
2
votes
0answers
35 views

ARIMA: How to understand performance of the model?

I am new to use of ARIMA model and after working on it for a couple of days and doing research - I'm not sure how to interpret the performance of my model... Here is what the ...
2
votes
0answers
36 views

Problem with Prophet Model regressior

I am working on predicting half-hourly UK electricity prices with prophet. I have two other time series: gas prices and initial national demand out-turn. So, after merging all the data-sets together ...
2
votes
0answers
28 views

Time Series and Statistical Learning methods differences

I am trying to understand the Time Series and Forecasting methods. I have this basic theoretical question about this: Why "Time Series" is NOT included on the Contents of, for example, the book "...
2
votes
0answers
21 views

Why might an LSTM be capable of predicting an ARMA signal but not a linear combination of ARMA signals?

I have an LSTM network and am testing it on some dummy ARMA signals. I'm trying to predict the signal 5 time steps into the future. The network is capable of outperforming Naive (persistence) when ...
2
votes
1answer
32 views

Building a time-series demand forecasting model

I am forecasting demand for certain types of goods and services, which I expect to be correlated to a sub-set of a basket of macroeconomic indicators (considering 15-20 indicators) I do not know ...
2
votes
1answer
2k views

Is there an R tutorial of using LSTM for multivariate time series forecasting?

There is a great blog post about how to use keras stateful LSTM in R to forecast sunspots. I applied it to financial ts data ...
2
votes
0answers
2k views

Monthly trend with fb prophet

I have monthly data with month/year in one column and price on another. I would like to get a yearly trend with fb prophet library in python (how to use monthly data with the library is explained at ...
2
votes
0answers
1k views

Understanding how to use ConvLSTM for multistep ahead forecasting

I have a problem where I have transaction data for many banking accounts. The task is to train a model on historical debit/expense transactions and then forecast expense transactions for the next n ...
2
votes
0answers
511 views

Recommended model for univariate or multivariate multistep ahead time series forecasting

I have a dataset consisting of recurring and non-recurring expense transactions from bank accounts, as well as other features describing the bank account and each transation. I aggregate these ...
2
votes
1answer
140 views

LSTM regression bias increases when targets go close to 0

I've build a LSTM model for time series forecasting. Results are not bad, with a mean normalized error of 7%. However, this normalized bias shows a clear pattern: The closer to 0 the value to predict, ...
2
votes
1answer
99 views

How do I use rnn to forecast to n periods with limited data?

So this is my 1st time trying to run a small time-series dataset through an RNN, but after a lot of searching, I haven't been able to find, 1. How I can use this to forecast to n periods ? (like in ...
2
votes
0answers
3k views

Error when using seasonal arima in python

...
1
vote
0answers
16 views

Vector Autoregression forecasting with large dataset

I am trying to use VAR to forecast electricity price for a whole day and I have a dataset with over 20000 observations (price for every hour) from 2015-2017. My first intuition was to select 19975 ...
1
vote
0answers
13 views

Does the R hts-Package work with time series of different units?

currently I'm having a look at the wonderful hts-Package. Its idea is to forecast hierarchical time series (like described here). In this example the unit of measurement across all time series is the ...
1
vote
0answers
26 views

Linear correlation and XGboost regression for time series

I am working with sales time-series data, I have a history of 9 years of monthly data. I am trying to forecast sales for the next 12 months. I am using XGboost regression to build multivariate time ...
1
vote
0answers
10 views

What are good public datasets for time series analysis with “certified” (by papers in the literature) good predictors of the target variable?

I have to test different models for time series forecasting and predictors (exogenous covariates) goodness evaluation and I would like to use datasets used in relevant scientific publications that ...
1
vote
0answers
52 views

How to combine data having similar distribution?

I have a collection of time series data with data points of around 2 years of daily data. I am thinking of a way to increase the number of data points in it so that the neural network gets a better ...
1
vote
0answers
9 views

Cross-validation for Timeseries Counterfactual Analysis

We are looking to predict counterfactual states from time-series data. In our problem we are looking to determine the energy savings from a grid-installed device that is varied on and off for many ...
1
vote
1answer
198 views

Forecasting multiple time series with a single model

I have a dataset with sales numbers for ~500 different markets (assume different cities or regions) and need monthly forecasts for each market. Instead of building 500 different models, I'm interested ...
1
vote
0answers
43 views

Is it possible to use LSTM for time series forecasting for future months with test data having only NaN values?

my dataset is a univariate time series with one column as months, other column having demands for the corresponding months. My test dataset has NaN vals only for all the months. Can LSTM be used in ...
1
vote
1answer
72 views

How to split a dataset into train and test sets for time series (multiple step-multiple output forecasting)?

I am trying to use an LSTM neural net to do multiple step / multiple output forecasting (I predict multiple values in one time knowing some values in the past). But, I have realized that I must be ...
1
vote
0answers
55 views

Finding p values and estimates of external variables in facebook Prophet for forecasting in Python

I am using facebook Prophet for multivariate forecasting which has an objecting of forecasting prices. My target variable is affected by n number of external variables too. I am using add_regressor ...
1
vote
0answers
102 views

Generalization of RNN/LSTM/GRU… model

Given a time-series prediction with a Recurrent Neural Network (doesn't matter if LSTM/GRU/...), a forecast might look like this: to_predict (orange) was fed to the model, predicted (purple) is the ...
1
vote
0answers
21 views

What approach should I take to model forecasting problem in machine learning?

I have a dataset which contains 4000k rows and 6 columns. The goal is to predict travel time demand of a taxi. I have read many articles regarding how to approach the problem. So, every writer tell ...
1
vote
0answers
158 views

How to apply an RNN to forecast non-stationary time series?

Is it possible to predict a time series which is non-stationary, in the sense that, the dependent variable Y have an increasing trend? Therefore, the highest value of $Y$ in the training set may be ...
1
vote
0answers
134 views

predictive clustering trees in Python?

I am faced with a time series forecasting cold-start problem, specifically I am forecasting energy consumption of businesses where historic consumption data is available only for training but not new ...
1
vote
1answer
84 views

Training data : forecasted or actual?

I am working on a time series prediction problem. I am using keras models for machine learning. For this prediction, weather variables are used as input. They can be of two types: forecasted and ...
1
vote
0answers
85 views

What's the difference between ELM and NNAR?

I'm working with time series forecasting using the two techniques that involve neural networks, the Extreme Learning Machine and the Autoregressive Neural Network. Reading the two methodologies, the ...
1
vote
0answers
31 views

Can I forecast with discontinued data using ARIMA?

I have data for sales on monthly basis, but a few months' information is not in the CSV file or data file. Can I forecast or fill that missing month with other calculated values from present records? ...
1
vote
0answers
77 views

How to model non-linear demand function?

I am trying to build a dynamic pricing algorithm on intermittent data (a lot of zeros between non-zero values). I have on average 100 non-zero data points for each product. However, it seems to be ...
1
vote
0answers
33 views

forecast product demand in one week using machine learning approach

I'm trying to predict product demand in store. The predictors I have include price, competitor's price, store ID, date. My target variable is sales volume (in a particular store). What I need to ...
1
vote
0answers
42 views

What kind of algorithm should I use to build ML model that can predict just next reoccurence of an event in the future (at irregular time interval)?

I'm quite new to machine learning and statistics. I've a dataset from some ecommerce sale's history. It's almost 2k instances, and features include personId (string), productCategory (string/...
1
vote
1answer
82 views

How is PACF analysis output related to LSTM?

I was going through a recent paper “A Novel Hybrid Data-Driven Model for Daily Land Surface Temperature ForecastingUsing Long Short-Term Memory Neural Network Based on Ensemble Empirical ...
1
vote
0answers
34 views

Can ARIMA be applied on a dataset of few months?

I have dataset of a few months of (time series) electrical load usage of multiple users. Can/Should ARIMA be applied for load forecasting considering that its not much data?
1
vote
0answers
92 views

Analysing spikes in demand to forecast future demand

I am trying to develop a system to predict future demand for different products at my firm. Currently, I have about two years of weekly sales data of a single product. My target is to predict the ...
1
vote
0answers
186 views

Predict the probability that a customer buy today

My company sells a single product that is a commodity. If you buy it, I can be sure that you will buy it again in the near future from me or from my competitors. The demand is affected by the weather. ...
1
vote
0answers
38 views

What values should I choose for P and Q?

I am trying to forecast energy data generated by LoadProfileGenerater. This data is generated every half hour for 2 years. I am following this tutorial. I have checked it for stationarity using ...
1
vote
0answers
359 views

Spark fitting into Data Science Paradigm for timeseries data

I have seen Dataframe as new API on Spark2 instead of RDD.So I have following few question about the utility of Spark in terms of time series data. Is forecasting still limited to memory available in ...
0
votes
0answers
20 views

How to do Goal Based Time Forecasting?

I have a yearly budget of $10,000 and I have my past monthly expenditure data. Using the past monthly expenditure data, I need to predict the date at which I'm most likely to exhaust my yearly budget. ...
0
votes
0answers
20 views

Transformer Decoding in Inference mode for Time Series

With the Transformer model from "Attention is all you need" you have to feed in the the actual target during training. However, this can obviously not be done for actual inference. Now usually for ...
0
votes
0answers
16 views

How to deal with a particular month being under forecasted by the model?

I have 6 cycles of historical time series data of retail sales and using a prophet model to forecast one cycle. I am using 4 variables as regressors. There is one month in particular - 'April', which ...
0
votes
0answers
30 views

Time series forecasting produce same values with different training data

I'm developing a python program which predict daily timeseries values. Each daily timeseries contains 288 values (a record every 5 minutes). The main idea is to train a LSTM model with 7 days data ...
0
votes
0answers
67 views

Does the add_regressor method on Facebook Prophet also work with categorical variables?

I went through the documentation of Facebook Prophet and was able to build a similar model for my time series dataset. The additional regressors I used were numeric. I achieved a reasonable MAPE score....
0
votes
1answer
30 views

Forecasting Consumption for Multiple Products for Multiple Regions

Came across a very interesting Real-World Time Series Forecast Problem. Can you please help me understand the right track to resolve the below Time Series problem: Input Data Sample: and we want to ...
0
votes
1answer
21 views

How to measure/rate the effect of a exogenous covariate in a ARIMAX Model?

I have an ARIMA model, I'm trying to figure out how much an external variable (exogenous covariate) could improve the forecast, so I need to "synthesize" a rate that tell me the usefulness (or impact) ...
0
votes
0answers
27 views

How to understand logistic trend parameters proposed by Prophet (Facebook)?

I read the paper and I saw that the logistic trend is defined as below : $$ g(t) = \frac{C(t)}{1 + \exp{ -k(t) (t - m(t)) }} $$ Where $k$ and $m$ are respectively a growth rate and an offset parameter....