Questions tagged [forecasting]
The forecasting tag has no usage guidance.
168
questions
0
votes
1answer
14 views
Time series forecast for everyday for till a distant future
I have time series data for every single day from last 5 years with seasonal variation and a general increase in trend. This is what my data looks like:
And I am trying to predict for every single ...
0
votes
1answer
11 views
LSTM's for timeseries with additional regressors
I have a dataset consisting of the weekly sales of 3,000 stores over the past 5 years, and have constructed a LSTM to forecast the next year of sales, given the previous year of sales. At each ...
0
votes
0answers
18 views
Why are Neural Network predictions “correct”, but offset from true value? Not using any past lagged values
I recently asked a similar question, but didn't get a response that really addressed/fixed the issue. Additionally, I've done some more work since then. I'm sorry for the long question below, I just ...
1
vote
1answer
26 views
What are some good methods to forecast future revenue on categorical and value based data?
I have monthly snapshots (3 years) of all the contract data. It includes following information:
Contract status [Categorical]: Proposed, tracked, submitted, won, lost, etc
Contract stages [...
0
votes
1answer
13 views
Best Approach to Forecasting Numerical Value Based on time series and categorical data?
Consider a dataset of thousands of car repairs that have been performed. In simplest of terms, the columns to consider are the time of year when it was broken (seasonal changes in demand for car ...
-2
votes
1answer
18 views
Accuracy of a forecasting model for prediction of COVID-19 occurence
My goal is to find the best performing forecasting model for the occurrence of COVID-19 in Toronto.
I pre-train the network with data on the occurrence of SARS in ten countries and Toronto. Then I ...
0
votes
2answers
33 views
How can I explain this chart showing 5-days moving average?
I have plotted the frequency of items sold through time, trying to determine the trends by moving average.
I considered a 5-days window. I would like to know if this approach makes sense and how I ...
0
votes
0answers
14 views
Time Series Analysis / Modeling with auto_arima
I recently dived into Time Series and was attempting at doing some data analysis and modeling. I'm using the following dataframe
...
0
votes
0answers
6 views
Ljung-box test on weekly percentage of total quarter bookings
I have a data on the weekly percentage of the total quarter bookings. The data looks as follows (note: weekly percentages add up to 100 for each quarter) :
(not real data)
I used the Ljung-box test ...
0
votes
1answer
16 views
Building Timeseries models for stock trading having multiple stocks
I have gone through some of the tutorials on the timeseries and all of them have taken one stock for the timeseries and tried to forecast it. My dataset contains many stocks for the time period(each ...
0
votes
1answer
22 views
Multivariate, Multi-step LSTM time series forecast
I'm trying to predict the Pollution using a Multivariate and Multi-step LSTM code, I've been following this tutorial.
I've been following the code until the end, but couldn't understand where the ...
0
votes
0answers
6 views
monte carlo simulation for impact to revenue by adjusting credit limits
I've been tasked with prioritizing projects for the year. One of them is to estimate the impact to net revenue if we were to adjust the purchase limits for our users. Our platform is transactional in ...
0
votes
0answers
16 views
RNN: Multiple inputs per time step with categorical variables
I am trying to a build RNN model to forecast daily sales for several different cities and different product segments (categorical features and multiple inputs for each day) along with numerical ...
0
votes
2answers
21 views
What are some good loss functions used to minimize extreme errors in regression and time series forecasting?
E.g. In detriment of a smaller mean error, I want to have fewer big mistakes
I'm working on a time series forecasting task and in some specific cases I don't need perfect accuracy, but the network ...
1
vote
1answer
22 views
best NN architecture for point prediction
I'm training to predict a single value y (continuos in [0,1]) based on a number of variables ...
0
votes
0answers
13 views
Trying to determine ARIMA parameters in time series
Hello I have a stationary time series with ACF and PACF plots as follows. How can I determine the p,q,d parameters with these graphs? Are they the lag values where the graph intersects the upper ...
0
votes
0answers
11 views
Preventing Overfitting with CausalImpact
I am looking to perform causal inference on a fairly limited dataset. The data is summarized monthly over the last few years, so I'm only looking at roughly 12-20 data points per time series. However, ...
0
votes
1answer
21 views
Energy price forecasting on timeseries
I try to predict electricity price based on several factors from historical data (consumption, consumption prognosis, wind power, wind power prognosis). All datasets I retrieve from Nordpool webpage.
...
1
vote
2answers
44 views
Time series forecasting: prediction and forecast far from the reality
Apologies for the awkward title, but I hope to be able to regain your confidence.
Let's start with the final output I got, so at least you can understand why I'm not happy/concerned about the outcome....
0
votes
0answers
9 views
How to make a multivariate forecasting if one of features becomes known for the future with some confidence level, e.g. weather forecast data
Let's assume that we make forecasting of another metric partially based on forecasts of the weather forecast, e.g. of temperature, pressure, then we can potentially obtain those forecasts from one of ...
0
votes
0answers
5 views
How could i change the frequence of Date time from None to a specific frequency
I have mixed data that contains a different date-time value, not daily or weekly and I don't know how to change the frequency from None so I can use the algorithms like Arima to it
2
votes
0answers
18 views
How to automate Seasonal Arima?
I am building Seasonal Arima for more than 10k products. In all the tutorials and blogs mentioned, I need to do the exploration to find the p,d,q values along with seasonality value using the ...
1
vote
1answer
24 views
Formulate multivariate multistep time series forcasting using traditional machine learning, NOT deep learning
How do you represent multivariate multistep data using traditional machine learning? I know this seems like a tailored problem for RNN/LSTM, but I am wondering what the alternative machine learning ...
0
votes
2answers
101 views
LSTM Multivariate time series forecasting with multiple inputs for each time step
I want to predict an output variable for the next day, for each of the users in my dataset. I was thinking of using LSTMs for achieving this.
The dataset
The dataset I am using has multiple inputs ...
0
votes
0answers
7 views
Train one model across multiple multivariate time series of diffrent duration, using categorical metadata
I'm trying to create model for prediction multiple correlated time series features.
Issue is that input dataset consists of a number of "projects" with different duration and different categorical ...
1
vote
1answer
18 views
Is my model to big? I am trying to predict orders for a company, and I don't know if there are typical values for macroparameters
I am building a model to predict orders, from its time series (univariate), for a company. I am working with 30 layers of 400 LSTM neurons each with the activation function hyperbolic tangent of Yann ...
0
votes
0answers
20 views
how do I approach forecasting problems using deep neural networks?
I am new to machine learning in general, and I have been requested to predict a price given a date. I have been trying to make a neural network for the task but it does poorly in the testing set, so I ...
1
vote
0answers
22 views
Multi-dimensional Time Series Features
I am new to applying ML to time series data but I do have experience doing general supervised learning. I have time series that is multidimensional (so several variables over time) with one output ...
1
vote
0answers
9 views
lags number in multivariate time series analysis correlation
I am trying to calculate the correlation coefficient(Pearson's r) of a financial time series $Y(t)$ and other exogenous variables $X_1(t),..., X_n(t)$. I am trying to understand the impact of my ...
0
votes
0answers
19 views
Multiple Values for One Day
I have two questions.
1- I have weather data of 10 turbines and I know their collective production(Power).I also know maximum power a turbine can make. How can I forecast collective production if I ...
0
votes
1answer
17 views
I am doing a forecasting for corona virus cases in NY, I have two models and not sure which one i should choose
I am using exponential smoothing and using tableau for forecasting. The first model I included trend and removed seasonality and it predicted the number of cases going up but the quality I got ...
0
votes
0answers
46 views
LSTM model for multi-step forecasting with multivariate time series
Im am trying to do a multi-step forecasting with multivariate time series, I have 9 variables (Y,X1,..X8) with 2270 samples for each variable, and I am trying to predict the future values of Y (70 ...
0
votes
0answers
22 views
Any good source to find nCOVID-19 latest trends and forecasts for analysis? [duplicate]
I am searching for trends and dataset in both .csv and api format to do predictive analysis on Coronavirus for various countries. What are good sources to browse such datasets?
1
vote
0answers
25 views
Aggregate results in time series forecasting
I'm working on time series forecasting with some sales data, with no exogenous variables, only sales per day.
After some analysis, including seasonal decompose, plot autocorrelation and parcial ...
1
vote
0answers
11 views
Forecast multiple unevenly spaced time series
I am building a time-series forecasting model to predict some patterns in climatological data.
The dataset consists of many (2 mln) time series which look for example as:
However the observations ...
0
votes
0answers
6 views
Are machine learning models good at autoregressive forecasting of time series?
AR, MA, GARCH and VAR models are standard for autoregressive prediction, which is the forecasting of a variable using its own historical lags for features/regressors.
Support vector regression (SVR), ...
0
votes
0answers
11 views
LSTM model for time series forecasting giving very poor performance even on training data
I am trying to perform timeseries forecasting with LSTM. I trained a model which is giving very less loss on training but when I try to predict the training data itself, it gives values far off from ...
0
votes
0answers
16 views
Forecasting binary time series
I am working on the next event occurrence prediction task and the data is binary time series with 1 if the event occured and 0 if not. I want to predict whether the event will occur or not on the day ...
1
vote
0answers
46 views
State of the Art/Research 2020 of Time Series Forecasting/Prediction
Im looking for the state of the art/research of time series data for forcasting/prediction.
As far as im aware it is Extrem Gradient Boosting (XGBoost) or LSTM (neuronal networks) or are there other ...
0
votes
0answers
18 views
MAPE over 100% after normalization of dataset
I try to forecast power demand for next 24 hours. Years 2017 and 2018 are my training set, 2019 is test set. I use multistep vanilla LSTM . In first step I used original data with any preparation and ...
0
votes
0answers
10 views
time series forecasting of time to leave for multiple customers using one model
I am a beginner in the domain of forecasting and I was wondering if such a problem could be solved with time series analysis :
given customer historical data of taxi pickups,along with the weather
...
5
votes
1answer
657 views
How fbprophet cross validation works
I am facing some issues to understand how cross_validation function works in fbprophet packages.
I have a time series of 68 days (only business days) grouped by 15min and a certain metric :
00:00 ...
1
vote
1answer
68 views
Python: forecast unevenly spaced time-series?
My data has timestamps corresponding to the failure occurrences of a specific component in machinery. The timestamps are not uniformly distributed.
My question is:
1) what methods can I use to (almost)...
1
vote
0answers
13 views
open source time series sales data for forecasting
I'm looking for open source time series sales data (past 2-3 yrs or more) that contains at least the following variables.
...
0
votes
2answers
58 views
Data Conversion to Time Series in R
I am having Sales data of 2018 and 19. I need to convert to time series. The data is not having daily sales
View(df)
Sales Date
75606 11/01/18
95620 16/01/18
55666 ...
1
vote
1answer
40 views
Forecasting with a Machine Learning Algorithm
Im sorry if it is a too general question, but i am stuck somewhere between perfect and adequate in my model. So, i wanted to ask here. If it is not a suitable question, your negative feedbacks are all ...
1
vote
0answers
14 views
How to forecast timeseries based on different events?
I have a few IoT sensors around my house that over time store some events with timestamps. Each sensor has a unique type e.g. ‘front’ or ‘back’. Let’s call this set X.
Now I have one sensor which ...
2
votes
2answers
40 views
What is an appropriate approach to sampling for probability of default using a classification model?
If we have a loan book and want to train the data to predict the probability of default, what is an appropriate way to sample the historical data to train the model, given that each account is open ...
0
votes
0answers
16 views
How to aggregate Confidence intervals?
Data Science community,
I am building out a forecasting model based on Facebook's prophet algorithm. The way our business is structured, we have multiple accounts rolling up to a parent account. My ...
1
vote
0answers
20 views
Time Series Forecasting with RNN/LSTM/NARX
I have some experimental datasets (like 4 or 5), and each dataset has three time series data, say $u1(t)$, $u2(t)$, and $x(t)$. The three time series of each experiment are similar but not the same. ...
