Questions tagged [predictive-modeling]

Statistical techniques used for predicting outcomes.

Filter by
Sorted by
Tagged with
-2
votes
1answer
60 views

model for univariate time series with 0,1 as data values

I am workig on a (univariate) time series data as follows. column 1 as (sequential) week index and second column with '0' (failure) or '1'( against each index for 104 rows). I need to predict the ...
1
vote
1answer
2k views

Xgboost (classification problem) feature importance per input not for the model

I have trained a xgboost model for a classification problem. I'm able to get the feature importance for the model as below. http://machinelearningmastery.com/feature-importance-and-feature-selection-...
0
votes
1answer
144 views

How to develop a good model for predicting electricity usage? [closed]

My goal is to come up with a set of research questions for which to drive my self study into my data. I have Smart Meter data that is taken every minute, on my home's power usage. How could I ...
4
votes
2answers
4k views

Xgboost quantile regression via custom objective

This is my first time posting, so please bare with me if I miss giving necessary info... I'm new to GBM and xgboost, and I'm currently using xgboost_0.6-2 in R. The modeling runs well with the ...
1
vote
1answer
427 views

export R neuralnet package model to PMML

when I look into the R package pmml, I found that, it is possible to directly export nnet model into ...
1
vote
1answer
56 views

An abstract idea for the performance diffs between SLP and MLP

Recently I am working on some predictive analytic which based on neural network. When I tried some tests on MLP with one hidden layer or multiple hidden layers, the results showed that: one hidden ...
1
vote
0answers
47 views

What is effect when I set up some self defined predisctor variables?

I run a random forest model on a dataset to assess the credit risk. I found the periodic income and periodic liability were important features in my estimator. Then I try to set a ratio metric which ...
0
votes
1answer
158 views

POC - Get an idea to create a Predictive Model

I'm trying to look for an idea to create a predictive model having the following data: ...
-1
votes
1answer
45 views

How to optimize the allocation of product aquisition

The scenario is purchasing of a product or raw material from multiple suppliers on a regular basis, and the problem is how to best allocate order quantities among the suppliers. For example need 100 ...
1
vote
1answer
135 views

Which machine learning algorithm should I apply for differentiate question difficulty level with users' result

Here's the scenario, There's a database with thousands of single-option questions for testing a specific skills, and a large number of users (either professional or amateur in this skill), each of ...
3
votes
3answers
471 views

Check Accuracy of Model Provided by Consultant

My company has recently engaged a consultant firm to develop a predictive model to detect defective works. I understand that there are many ways to validate the model, for example, using k-fold cross-...
4
votes
2answers
197 views

What is a better approach for cross-validation with time-related predictors

I was a given a data set with different predictors about a store and the idea is to forecast the number of daily shoppers. The predictors are the weekday, time of the day (morning, afternoon, evening),...
2
votes
3answers
102 views

Methods to reduce dimensionality within a feature?

Suppose that I am interested in predicting an outcome (say, the arrival delay [in seconds] of a flight) based upon a set of features. One of these features is a nominal variable - ...
1
vote
1answer
373 views

Best MIMO prediction algorithm for categorical variables

I have researched machine learning for quite a while and would like to test out my knowledge. So I am trying to use it for lottery number prediction. The goal is not to have 100% correct prediction (...
0
votes
1answer
144 views

gold price detection using data mining

I have dataset of gold prices and after modifying and some preprocessing i ended up with dataframe below: There is 50,000 record in dataset and all columns expect ...
0
votes
1answer
646 views

What are recommended methods for multi-task prediction?

Currently, we are working on a school project which is trying to predict the number of crimes in some area/neighbourhood. There are 8 different categories for crimes and we've tried to find the ...
4
votes
1answer
4k views

Use TSFRESH-library to forecast values

Have some issue with understanding how to use TSFERSH-library (version 0.4.0) to forecast next N-values of particular series. Below my code: ...
3
votes
1answer
391 views

How to handle data collecting bias in machine model training

In many ML problems we collect data and train models using the collected data. Using recommendation as an example, data collected could be biased for various reasons: presentation bias. For example, ...
1
vote
1answer
57 views

Imbalance in observable data

I am studying the performance, over 10 years, of high school students that enrolled in a school district. My Objective is to make inferences about factors leading to poor performance in school exams. ...
0
votes
1answer
60 views

Estimating forward velocity for a swimmer

With a modern IMU with 9 angles of freedom collecting accelerometer, magnetometer and gyroscope data on 3 axis, what would be the best approach on filtering the data and handling it to accurately ...
3
votes
2answers
2k views

fix first two levels of decision tree?

I am trying to build a regression tree with 70 attributes where the business team wants to fix the first two levels namely country and product type.To achieve this,I have two proposals: 1.Build a ...
3
votes
2answers
111 views

Prediction approach on unique data or progressive data

In a employee attrition analysis with a table having rowwise data for a (employee like Id, name, Date_Join Date_Relieving Dept Role etc) ...
2
votes
2answers
4k views

Methodologies for predicting missing data

I have the following problem: I'm searching for methods to predict randomly missing data in a given dataset. For example: I have a dataset which contains information about a person. This can be ...
2
votes
1answer
107 views

Different models for different time durations of a day

I have hourly temperature and power consumption data of several days of a month. The pattern is almost similar across days like this: Using this data I want to predict the usage of a coming day. I ...
1
vote
1answer
44 views

software for workflow integrating network analysis, predictive analytics, and performance metrics [closed]

I am hoping that there is some existing software for what I want to accomplish, as I'm not a big fan of reinventing the wheel. In general, I would like a software package that can serve as a workflow ...
0
votes
4answers
202 views

Deploying the prediction model under missing values for test data

I have successfully built a logistic regression prediction model based on data set that is complete and clean, i.e., there is no missing values and the data is consistent. Now, for deploying the model ...
0
votes
1answer
361 views

Models systematically underestimate values on the test set, why?

I used different models to train on the test set and to predict on the test set. The commonality is that all models underestimate the true values on the test set. Which steps should I take to ...
1
vote
0answers
369 views

Sklearn Random Forest Prediction Correlation Issue

I'm having issues with fitting a Random Forest model to a completely new dataset. I'm trying to predict tenancy lengths for current tenants. I have a dataset with tenancy information since 2008, with ...
2
votes
0answers
1k views

How does Elastic's Prelert (formerly Splunk Anomaly Detective App) work?

Background: In recent months, Elastic has purchased Prelert and will actively incorporate it into the Elastic stack (and also discontinue the Splunk Anomaly Detective App!). I am trying to understand ...
3
votes
2answers
9k views

Xgboost predict probabilities

When using the python / sklearn API of xgboost are the probabilities obtained via the predict_proba method "real probabilities" or do I have to use ...
1
vote
1answer
235 views

Regression in Predicting Tenancy Lengths

I'm currently working on a project involving the prediction of tenancy lengths. I've so far managed to get to a point where I've processed the data and pruned my Random Forest model (via sklearn in ...
2
votes
1answer
524 views

Which algorithms should I use for recommendation system using a graph database?

Basically I'm developing a recommendation system using a graph database (specifically neo4j), and I want to apply recommendation algorithms. Since i'm using a graph database, I can see the ...
2
votes
1answer
181 views

Period Predictive Model

I am not sure how to formulate this problem clearly into a machine learning task yet. So hope you guys can chime in and give me some help. Problem : To predict whether someone will pick up their ...
1
vote
1answer
685 views

Predicting a numerical value based on past values and categorical attributes

I have training data consisting of a time series of numerical values (e.g. a user activity metric on a website over a period of 100 days). I also have some categorical attributes of the user (...
5
votes
1answer
5k views

How to use survival analysis for predictive maintenance for time series data?

So, I have a dataset with daily operating conditions for different machines and a flag saying if it failed or not. Here is a snapshot of the data. How can I use survival analysis or any other ...
4
votes
4answers
360 views

How can conclusions be drawn from recommendation systems evaluation?

From my research, a recommendation system are a subclass of information filtering system that seek to predict the "rating" or "preference" that a user would give to an item. And basically exists many ...
2
votes
1answer
439 views

model with only positive responses

Could any one help me know about different approaches, methods or algorithms to build a model only with positive responses. Let's assume we have a set of customers with a 'positive' behaviour. We ...
2
votes
1answer
449 views

Do categorical features always need to be encoded?

I'm using Spark's Machine Learning Library, and features are categorical. The features are strings, and Spark's MLlib (like many other machine learning libraries) does not accept Strings as inputs. ...
1
vote
1answer
164 views

Autoregressive Moving Average ARMA with statsmodels

Can I please get direction on what is wrong in the code? All forecasts provide output except the ones listed bellow. so basically doesn't pick ['UserDefinedData4'] ...
9
votes
2answers
2k views

Machine Learning Best Practices for Big Dataset

I am about to graduate from my Master and had learnt about machine learning as well as performed research projects with it. I wonder about the best practices in the industry when performing machine ...
5
votes
3answers
1k views

Balanced Train set to predict Imbalanced Prediction set

One of the methods to address a classification predictive analysis on an imbalanced set consist on undersample the majority class (others approaches consist on: undersample the majority class, ...
1
vote
4answers
427 views

Discrepancy between training set and real-world data set: domain adaptation?

I have read in literature that in some cases the training set is not representative for a real-world dataset. However, I cannot seem to find a proper term describing this phenomenon; what is the ...
1
vote
1answer
289 views

Neural Network - Adjust number of hidden layers and neurons

I am using KNIME MLP Neural Network learner (If you are not familiarized with KNIME think of that like a package which implements Neural Network to a set of data). The thing is you can tune the ...
3
votes
1answer
92 views

Putting dirty data back into a model

Suppose I am processing 3rd party vendor error log files that I am unable to change the schema from the source. And I am trying to predict a label. Once logs are collected and I have all I need, in ...
-2
votes
3answers
429 views

How to calculate “Revenue of next order per customer”?

I have transactional data of an online store. How can I predict the "revenue of next order per customer" or "time until next order per customer"? I have following columns: ...
2
votes
3answers
1k views

How to use ML to forecast sales of a brand new product

I am working on a forecasting problem and came across this issue. How do I forecast sales of a brand new product? For example, a product has been introduced in the store and the store would like to ...
1
vote
1answer
175 views

Python: how to handle categorial values in dataset to build models

I have a training dataframe dfTrain and the output of dfTrain.head() is shown below: ...
2
votes
1answer
246 views

Missing Categorical Features - no imputation

I've been reading about how to approach missing categorical features in test data, and the most common approach is to use imputation - for example using the last known value or getting the majority ...
2
votes
0answers
345 views

wrong prediction from graphlab.recommender.item_similarity_recommender

I have a question about basic understanding of how item-item collaborative filtering of "Graphlab" library works. I run this code: ...
1
vote
3answers
148 views

Method for predicting price based on Geographical market, Product, and Company

I have a dataset which tracks the prices of 21 products, charged by 24 companies, in 150 different cities across the globe. However, the data set has missing values--that is, I might have Company X's ...

1
12 13
14
15 16
18