Questions tagged [predictive-modeling]
Statistical techniques used for predicting outcomes.
1,199
questions
0
votes
0
answers
15
views
P value for partial least squares regression in python
is there a way to calculate Pvalues for Partial Least Squares (PLS)? Or any preferred method to evaluate coefficient significance for PLS method? Preferably done in python
- 11
0
votes
0
answers
17
views
Predicting contract renewals with a linear regression model
Good day all
I have an idea where I want to predict contract renewals over time for a service based company. Essentially, taking the total amount of times a customer decides to renew their contracts ...
- 1
0
votes
0
answers
12
views
Difference between Train AUC and Test AUC in MaxEnt
I would like a clear explanation of the difference between the train AUC and test AUC in MaxEnt. How is it calculated based on my input data? Is it the train AUC that is the average of X iterations, ...
1
vote
1
answer
34
views
How to model a polynomial function with many features and multiple outputs
With linear regression (and multiple linear regression), one can have many features but only one output as y. I need to build a model with multiple x's that also outputs multiple y's in a polynomial ...
- 11
2
votes
0
answers
47
views
How to retrain your model when the old one impacted your new data?
There are several tutorials and courses explaining how to monitor a model, discussing data drift and the need to retrain our predictive models occasionally. However, when I think about it, I encounter ...
- 61
0
votes
0
answers
15
views
Expecting your comments to structure my project?
I am developing an binary classification project. Initially I got a dataset including real data in 3290 rows and 15 columns. Then using CTGAN network I generated synthetic dataset with 100000 rows. ...
0
votes
0
answers
23
views
When can a low r-squared generate a good predictive models?
Most discussions on model prediction says that you should focus on error metrics, like RMSE, MSE, MAE or MAPE. Some even argue that r-squared can be low in a good model. However, I can't think of a ...
- 61
1
vote
0
answers
20
views
Using a prediction from a First Principles Model in a second, statistical model to improve accuracy
I am trying to figure out what this is called, so I can do some reading on it and see which types of statistical models excel in this framework (and known pitfalls to avoid). I have been calling it a ...
- 11
0
votes
0
answers
20
views
Time series modeling tips
I'm currently building a pricing time series model for a category in produce and I have some questions. This is my first time building a forecasting model at my job and I've hit a few road bumps.
The ...
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
1
vote
0
answers
18
views
python model to predict future performance
I would like to build a python model to predict how a student will perform on a given math test. I have data relating to each student and also their score on up to 100 previous tests that (each ...
- 11
0
votes
0
answers
16
views
Impact of Adding Imbalanced Data on Model Performance for Different Groups
Suppose I initially have a dataset with 50 samples of type A and 50 samples of type B, each with several features. I built a neural network model using this data and recorded the prediction accuracy ...
- 1
1
vote
1
answer
37
views
How to evaluate the performance of a prediction model across multiple predictions of the same event?
I was thinking of a hypothetical situation where you have a prediction model that can be used to predict the winner of an upcoming football match between Team A and Team B.
Say for the sake of the ...
- 13
1
vote
0
answers
40
views
I need some advice about working as Mathematical Modeler/Data scientist [closed]
I have 10 years experience in studying mathematics in University, and I've just finished my Masters degree
I have some experience with LaTeX and Mathematica, what do I need to study to be able to ...
- 11
0
votes
1
answer
53
views
How can I improve my predictive model?
Here is my interpretation of my model so far, I am investigating the relationship between ratings and followers on video games, but there is a problem. The more you get high ratings, the more you get ...
1
vote
1
answer
35
views
Feature Engineering a Recency feature
I have a customer scoring problem I'm working on specifically on predicting conversion and coming up with a probability score on conversion (using xgboost classifier atm). There's a feature I want to ...
- 11
2
votes
1
answer
189
views
Optimized input data structure for ML model training
I have a large dataset (20M+ rows) of user interactions which I want to use to predict the probability of a customer purchasing an item in one-, three- and six months time. However since the ...
- 21
0
votes
1
answer
42
views
Random forest regression model for stock price prediction output has a flat line in the predicted values during the initial values
I have a random forest regression model for predicting the close price for stock data. I am getting model accuracy as like this:
/n Best Parameters: {'max_depth': 10, 'min_samples_leaf': 2, '...
- 1
1
vote
1
answer
27
views
Does performing k-NN on the centroids of clusters obtained from k-means make sense mathematically?
While playing around with some text embeddings, I used k-means clustering to get 4 clusters. I also have the labels for these embeddings, and I may simply use k-NN to classify new embeddings. However, ...
- 113
1
vote
1
answer
108
views
How do I work with time-series data of temperature?
So I have some equipment temperature and i have outside temperature (both are collected daily) and I want to predict the equipment temperature. However, I'm new to this and unsure about which model to ...
- 11
0
votes
1
answer
66
views
Build a Neural Network for Multi-output Regression
I have a network model that accepts about 25 inputs and outputs 3 actions.
The outputs are: delta X and delta Y of the robot and the angle of the robot.
After I enter the data into the model, I get ...
- 1
0
votes
0
answers
8
views
Combing Output of Two Regression Models
I have two models.
Model 1:
I have a dataset of American high school students and their test scores and other characteristics. I built an ARDRegression model that predicts how well a student will ...
- 1
0
votes
1
answer
31
views
handling predictions with optional or missing features
We have a few variables that are highly predictive in our modeling task. Is it sound to train models with a superset of features even though some are known NOT to be available at predict time? & ...
- 351
0
votes
0
answers
12
views
Machine Learning Algorithm for identifying the factors contributing to academic performance of students
I have a dataset with several qualitative and quantitative attributes, including age, location (longitude, latitude), city, parent occupation, family size, GPA etc.
My task is to find the attributes/...
0
votes
0
answers
32
views
How to predict inside of the box temperature at a give outside temperature using python?
I Need help predicting inside of the box temperature at a given outside temperature.
Background
I have a system (also known as a BOX). The BOX is insulated from the outside environment and contains ...
- 1
0
votes
0
answers
10
views
Best subset selection includes predictor with high p-value
I'm trying to use subset selection to find out the best model according to AIC. However, it is recommending a variable with a p-value > .9. My guess is that this is because the subset selection ...
0
votes
0
answers
18
views
İnternal and hold out test for shap
There is an internal test set and a hold out test set. I explain the model with Shap library. Should I use the internal test set or the external test set? What should I do if there is a difference?
- 1
0
votes
0
answers
6
views
How do I determine syndicate and collusion indication with clustering and network analysis on a large unlabeled user transaction data?
How do I determine syndicate and collusion indication with clustering and network analysis on a large unlabeled user transaction data?
So far, I've only been training with labeled data on fraud-...
0
votes
0
answers
32
views
Select estimators for Voting classifier
I don't know the efficient method to select the best subset of the estimator that saves time and highest accuracy. How to choose the best estimators for the Voting classifier?
Voting Classifier is an ...
0
votes
0
answers
13
views
ANFIS Model, tips about improving performance
I have a question regarding about improving the performance of an ANFIS (adaptive neuro Fuzzy inference system) model.
In MATLAB, I have been training a model with 5 inputs, with 816 data point for ...
0
votes
0
answers
11
views
how to obtain predictions for all observations in a dataset?
I have a dataset comprising 1864 roads with various traffic and safety features, along with the number of accidents at each road. The objective is to rank these roads based on the number of accidents. ...
- 1,307
0
votes
0
answers
13
views
LSTM Model for Multivariate Multi-Series
I'm looking to create an LSTM model to predict a certain label trained on multiple short-time series data. How would I go about doing this? Each time series has 10-30 time steps and 20 different ...
- 1
3
votes
1
answer
64
views
When do you know training a model is not feasible?
A couple weeks ago I volunteered to take on a project at work to try predicting the ideal price rental cars my employer should be charging based on our historical rental data. The variables available ...
- 31
0
votes
1
answer
23
views
Does ANN returns the same prediction for the same input?
Does ANN predictable? By this I mean that if I re-run the same script over and over, does it make sense that the error (MAE / MSE / R^2) is different on every run?
if true, then a follow-up question: ...
- 163
1
vote
0
answers
34
views
Standard Error interpretation help
I performed a standard error on my machine learning model to predict protein structure. The graph Im showing here is a snippet of the actual data and I deleted some irrelevant info. The y axis is the ...
- 11
0
votes
0
answers
22
views
Differentiating between runs that start at different timestamps
I have a CSV file of the latitude and longitude coordinates of trains in the format [timestamp, runID, latitude, longitude].
The problem is that I have tracked ...
0
votes
1
answer
39
views
What's the best model choice for a non-linear regression task?
I have a dataset with the following format:
Rows: 3700,
float_columns: 17,
int_columns: 2,
categorical_columns: 12
Target Type: Continous, float
My dataset is an insurance dataset that stores the ...
- 671
1
vote
0
answers
52
views
How to Yield a Better AUC / Lift Score?
I have a dataset with 200k records and 173 features focused on binary classification. Class proportion is around 98.7:1.3 (1.3% target=1).
Currently, I am trying to increase the performance of my ...
- 11
0
votes
1
answer
75
views
Sale Forecasting Problem -- Is it legit to use inventory level as a feature?
I'm working on a project to predict future sales for our company's products so that the supply chain can have better idea how much to restock.
Detail about the model I'm working on:
Model: LGBM (from ...
0
votes
0
answers
20
views
How to use two independent datasets in machine learning phd research work?
In order to develop an academic performance prediction model for a local Higher Ed Institution, I have collected the OULAD open dataset and the local Institution's dataset which I structured into the ...
- 1
0
votes
0
answers
15
views
Prediction with optional parameters
I want to build a machine learning model that has 25 input feature and two labels (my problem is a regression task if it makes any difference), to my knowledge since I have two labels I need two ...
- 23
0
votes
1
answer
53
views
Ideas on building models to predict the likelihood of prospects converting (making their first purchase)
context: I have a task to identify the prospects who have high or medium likelihood of making their first purchase after they signed up for 30 days, so that our marketing teams can take actions for ...
- 3
2
votes
2
answers
56
views
Handling Month-over-Month data in Regression Model
I have data similar to what you see in the picture. I want to use a RandomForest Regression model where I can use fields (excluding MONTH_END_DT and LOCATION_ID) to predict REVENUE_PER_UNIT. The idea/...
0
votes
0
answers
28
views
Using simple RNN to identify a simple dynamic linear system
I have been trying to identify a simple linear second order system (e.g. a pendulum or a mass-spring system), by simulating it in Python using backwards-euler method and then feeding the step changes ...
- 1
0
votes
1
answer
151
views
Effect on regression coefficients by multiplying a constant to a feature
I was solving one quiz question on Coursera and I found an interesting question.
If you double the value of a given feature (i.e. a specific column of
the feature matrix), what happens to the least-...
- 165
0
votes
0
answers
17
views
How to approach this problem?
I have 3 large datasets with 21 non-ordinal categorical variables and 1 variable date, representing data from month intervals in two years. The target variable is a categorical variable with multiple ...
0
votes
1
answer
33
views
I am a beginner in Knime and using Random Forest
Within Knime how am I able to identify which of the variables have the best predictive power within my model. I have successful ran the model and assessed model accuracy, recall and precision but can ...
0
votes
0
answers
28
views
How to reduce number of continuous variables before I make a set of best predictors (for handgrip strength in women)
My assignment question is quoted: "2. Which set of variables best predicts handgrip strength in women? a. Reduce the number of continuous variables before doing the analysis."
I do not ...
0
votes
0
answers
38
views
LightGBM Regressor miscalibratred/underestimating on high fitted values and overestimating on low fitted values
I'm training a pretty standard LightGBM regressor and noticing a strange pattern with the residuals (see images below--I'm bunching the predicted values and taking the observed average for the group). ...
- 101
0
votes
2
answers
199
views
Best model for regression in this case?
I am doing some modeling to predict a variable of interest given a big set of features (500) for which I expect a considerable amount of interactions happening at least among some of them.
I first ...
- 111