Questions tagged [forecasting]
Forecasting is the process predicting future values based on historic and current data, typically for time-series datasets.
349
questions
0
votes
0
answers
6
views
Feedback Loop in Prophet Model (Using predicted vs Actual data to improve future predictions)
I am working on a sales dataset which has historical sales on a daily basis for 10 products (SKU) ranging through 2 years on a daily basis up to date (Including zeros for days with no sales). To ...
0
votes
2
answers
24
views
XGBoost gives same answers for parameters not in training range
I have a data set (CPP(Monthly average), Channel, Show, Month, Year) for marketing return prediction. Data set has ads from 2022 to 2023 with about 130k points. I have a model, XGBOOST, and Train, ...
0
votes
0
answers
6
views
"Model" parameter in cross validation function in prophet
I have been using Prophet model to for demand forecasting. I have a general question about how I should be using the fitted model input to cross validation function.
...
0
votes
0
answers
9
views
Is it appropriate to utilize LSTMs for multivariate binary prediction on a timeseries by sliding block-by-block vs row-by-row?
I am trying to implement an ML algorithm for multivariate regression on a list of several timeseries. There are hundreds of timeseries, each one millions of rows long. There are 13 features, and I'm ...
0
votes
0
answers
16
views
How to Predict Remaining Lifetime or Replacement Probability of Machine Parts?
I am diluting and abstracting away some details to protect the client, but the basic idea like this.
Context
An authorised vehicle service centre run by a company, something like Audi, where vehicles ...
- 335
0
votes
0
answers
10
views
ARIMA Hyper-parameter values for different sets of test data
I am building a monthly ARIMA forecasting model. The data I have is from last Sept, (09-2023) until May this year (05-2024). I built an ARIMA model after grid search using ...
- 101
0
votes
0
answers
58
views
Change point detection in a timeseries
I have a few questions about using the PELT algorithm for change point detection in the ruptures library.
Optimal Penalty Value for PELT Algorithm
I'm using the Pruned Exact Linear Time (PELT) ...
- 1
0
votes
0
answers
18
views
Implementation of CNN-LSTM for multivaraite time series forecasting
I have recently completed the course on TimeSeries from Coursera - Deeplearning AI, and was trying to replicate the results of an open-access research paper (...
0
votes
0
answers
9
views
How to model a marked temporal point process with unboundedly evolutionary integer event markers
I have a marked temporal point process (MTPP) where the number of discrete event types is unbounded. Each type of event occur several times and never happen again. For example, in a given time frame, ...
- 15
0
votes
1
answer
58
views
0
votes
0
answers
8
views
Is this recursive forecasting right for timeseries analysis?
Training a model just to make a quick prototype
...
1
vote
0
answers
25
views
How to predict Future CPU Usage in Time Series reusing your already trained model?
I'm currently working on a time series problem where I need to predict future CPU usage. I have historical data consisting of CPU usage along with features like hour, day of week, and month. However, ...
2
votes
2
answers
56
views
How best to explain Forecasts when model cannot be accessed?
My company purchases demand forecasts from an external vendor (after providing them with our historical data). My manager wants to explain the forecasts that we are receiving and has requested for ...
- 53
1
vote
0
answers
34
views
Time series windowing approach
I have this problem statement from my project is that base on the 5 mins data to predict the next 2 minutes. (you can look at the top) each segment of 5 minutes predict the next 2 minutes.
However, is ...
1
vote
1
answer
94
views
Multivariate Time series forecast deep learning
My Dataset:
I have data for vehicles - mainly engine sensor data but also gps location, weather etc.
The data is high frequency - every second. I have aggregated to 1 minute.
I roughly have somewhere ...
- 13
0
votes
2
answers
18
views
Technical Term for Multivariate Time Series Forecasting with different input output features?
What is the technical name for multivariate time series forecasting where the input and output features are different? usually, the dimensionality of the input and output is the same when we use the ...
0
votes
0
answers
36
views
Multi-step CNN-LSTM Encoder Decoder Model is not fitting well on peak values
I am trying to predict 4 values concurrently for next 24 hours
n_lookback = 48
n_forecast = 24
I am breaking the sequences like this:
...
-2
votes
1
answer
37
views
I need suggestion for a project
I want to make a forecasting system which will forecast how much quantity will be sold next year based on the previous 5 years' data from 2019 to 2023 and want to predict for future years. Now the ...
- 11
0
votes
0
answers
37
views
Forecasting Resource Depletion in a Distributed System
I manage a distributed system where each node contains six interchangeable resource slots, sourced from a diverse pool of resource types. Each type has a finite number of units, which get consumed ...
- 101
0
votes
1
answer
23
views
Does nowcasting use cross sectional data?
So in recent months I have been reading about nowcasting. From what I understand what UMIDAS does is that it transforms the dataset into cross sectional data and then runs OLS.
The more I read ...
- 1
2
votes
1
answer
82
views
Univariate time series forecasting with bimodal distribution
This is my first ML project ever.
Well the objective is to build a forecasting model of a univariate time series containing solid waste weights loaded from the city of Austin,Texas.
The distribution ...
1
vote
1
answer
39
views
Misaligned Multivariate Time Series (weather and soil moisture) in soil moisture forecasting
I'm working on soil moisture forecasting using multivariate time series (MTS). More precisely, each time sample comes with multiple measurements regarding: the soil (e.g. soil temperature, and soil ...
- 11
3
votes
2
answers
196
views
How bootstrapping works for prediction intervals?
I'm experimenting with prediction interval (PI) over univariant time-data using skforecast pythonic package..
in the documentation it is mentioned that:
Prediction intervals
A prediction interval ...
- 400
0
votes
0
answers
39
views
Time Series forecasting with SVR
I am trying to forecast my data by Support Vector Regressor,
Here is my code:
...
- 1
0
votes
0
answers
15
views
How to correctly use gstar package of R for spatio-tempral analysis?
I want to perform a spatio-temporal analysis by highlighting spatial as well as temporal dependencies of the data (I have a 'weight matrix' highlighting spatial dependencies of the counties) on the ...
0
votes
2
answers
126
views
Time Series forecasting feature creation/engineering
I'm new to time-series-forecasting and was wondering, whether in a single variable forecast e.g.: X -> Y the creation of additional features of X leads to an improvement when training.
So if adding ...
0
votes
2
answers
134
views
Is there a way to check if a time-series is seasonal without manual inspection of its decomposition?
While using various models to generate a forecast of a time-series it is needed to know if a time-series is seasonal or not.
I have searched about this topic but could only find people mentioning ...
- 103
0
votes
1
answer
272
views
Calculate the best alpha, beta and gamma that should be used in the holt-winters exponential smoothing formula
With the following code I can find the best forecast value for a series by iterating over the alpha, beta and gamma and saving the result with the best RMSE:
...
- 103
0
votes
1
answer
25
views
How to add lagging Features for Forecasting with a random lag range without adding a new column per lag?
The common way of adding lagging features in time series forecasting problems is adding lag columns with pandas.shift(). While it is a fine method but what about when wanting to use a random integer (...
- 151
0
votes
0
answers
27
views
Gradient boosting to forecast just one-step ahead
I'm training a gradient boost algorithm (trying both XGBoost and LightGBM) for cash flow forecasting. I was able to do it well separating my training and test sets using the default separation (80/20) ...
2
votes
1
answer
136
views
Should I remove or interpolate missing values?
I have a dataset containing a very long time series of hourly traffic congestion in a certain city, during a period of ~22 years (number of data points: Roughly 24 X 365 X 22 = 192720). I want to use ...
- 23
3
votes
0
answers
42
views
How to predict multi-variate time-series from different samples [closed]
I'm having issues seeing the best way to predict a time-series when training on a dataset with different samples.
I have a dataset that shows the weight of 10 rabbits from their first day to their ...
- 31
1
vote
1
answer
495
views
When is it necessary to remove seasonality from multivariate time series?
I have a complex time series dataset that I'm exploring (https://archive.ics.uci.edu/dataset/501/beijing+multi+site+air+quality+data) and I've detected some regular hourly seasonality in the data (not ...
- 113
0
votes
2
answers
275
views
How to detect and predict sensor faults and failures (for weather stations to be specific)?
Need help. Especially those knowledgeable in weather systems/meteorology.
Best approach in detecting and predicting faulty weather sensors and their failures based on their readings alone?
I'm doing a ...
- 1
0
votes
0
answers
49
views
Forecast proportions through time
I want to predict/forecast the proportion of positives (sample testing positive) over a 1-3-6 month period. My data has a lot of negative sample tests, therefore, it's aggregated by month. Let's ...
0
votes
0
answers
13
views
Correlation in forecast error
I am working on a time series project and while calculating the prediction intervals using bootstrapping method I have to fulfill the assumptions of it. It has an assumption of uncorrelated forecast ...
0
votes
0
answers
17
views
Demand Forecasting methods for hundreds of time series
I have TFL cycling dataset for the time period from JAN 2023 to JUNE 2023. I would like to forecast the demand or expected no. of trips for each station at every hour of the day.
Post some data ...
- 197
0
votes
0
answers
21
views
Lack of Variability in Predictions from Multivariate LSTM Model
I've been working on a multivariate LSTM model for time series forecasting, but I'm encountering an issue where the predicted output doesn't exhibit enough variability. The predictions tend to be too ...
- 101
0
votes
0
answers
14
views
Is it possible to use leftovers data (warehouse stocks data) to create sales forecasting?
For example, i have sales data by categories
| Date | GE | VIC |
| -- | -- | --|
|03.01.2022 |2|7|
|10.01.2022 |30 |12|
|17.01.2022 |15 |5|
|24.01.2022 |57 |8|
|.....|...|...|
|28.08.2023 |16 |2|
And ...
- 1
0
votes
0
answers
38
views
Winter Holt's Time series model
I am confused with the Winter Holt's Time series model usage. I use 2 years of data to train and want to predict 3rd-year data.
Note1: I have partial 3rd year's data, but I want to use it to check my ...
- 1
0
votes
1
answer
140
views
Can lag features be applied into test data without label?
can lag features be applied into test data without label? I've been wondering. I tried to build random forest model using dataset: training data (with label Y) and testing data (without label Y). The ...
- 141
0
votes
0
answers
15
views
Stable test in online time series forecasting problem
I have a Time Series Forecasting problem. You can think of it as predicting the daily closing prices of Apple stocks. My data is divided into 4-day segments, and the forecasting is based on predicting ...
- 63
0
votes
0
answers
12
views
How do we modify the early stopping procedure to account for better losses after initial rise in losses?
I have a question regarding the usage of early stopping in the training of my forecasting model. Curious about how the training would go without early stopping, I observed that the test loss seems to ...
0
votes
0
answers
28
views
Can a multivariate MIMO LSTM forecaster learn the relationships between the multiple feature outputs?
Question: Can a multivariate MIMO LSTM learn the relationships between the multiple feature outputs?
This question arose when I decided to modify a multivariate (Multiple Input - Single Output, MISO) ...
0
votes
0
answers
22
views
Predicting quanting sold using Time series data
I am struggling with a time series dataset comprising 12 features, including quantity sold and weather data, totaling approximately 1800 values. My goal has been to forecast future values, quantity ...
- 1
0
votes
0
answers
38
views
Calculate the curve of a list and apply that to calculate the values of a larger list
I have a list of ~125 sorted ascending values and I am converting those to percentages of total so that they add up to 100% (shortened example would be: 0%, 0%, 15%, 15%, 30%, 40% with the total of ...
- 1
0
votes
1
answer
351
views
How to assign sample weight for regression problem
I'm trying to model a forecasting problem where I'm trying to forecast for the following month. I am using LightGBM Regressor class for it and it giving me a decent ...
1
vote
1
answer
96
views
Is timeseries forecasting for the next timeslot with a RNN a "Many-To-One" type application?
you often find applications that divide RNN according to their input and output data into the categories:
One-To-One
One-To-Many
Many-To-One
Many-To-Many
as you can see e.g. (here https://...
- 83
0
votes
0
answers
26
views
Forecasting using LSTM Model
I have a dataset with 12 variables (x1, x2, ..., x12) and one target variable (y). Is it possible to perform a forecasting for the target variable (y) over a certain period of time ahead without ...
- 1
0
votes
1
answer
128
views
Prediction intervals for future timestamps - out-of-sample
I've created a model for out-of-sample forecasting that uses multistep recursive strategy to reduce my problem to regression, the predictions are sufficient but I was wondering if there is any ...
- 1