Unique ETA prediction vs continuous ETA prediction
$begingroup$
Currently I have a predictive model, which predicts ETA flight times. Specifically, this is a regression that predicts the flight time that results from some features and the target variable:
Flight_duration = Arrival-time – Airborne time
This specified flight time is added to the Airborne timestamp to predict when it should be there.
Now I want to extend the model. It should no longer be predicted once at Airborne, but several times during the flight to improve the ETA forecast.
I got real-time flight data for that. There are now several lines with timestamp + coordinates for a specific flight where it is located.
The question I ask now is, how do I model exactly?
How can I use the coordinates optimally as a feature (as a geohash?)? Should I see this as a time series prediction? For example, I push the last t-3 features..for example geohash and how long the flight_duration to these points was in the model and forecast e.g. always the t + 1 flight duration.
Currently I use a Gradient Boosting model, which is quite good for a forecast at the Airborne time. For example, I have an RMSE of about 8 minutes at 12 hours flight time.
Do you have experience and can you share it with me?
machine-learning time-series
New contributor
$endgroup$
add a comment |
$begingroup$
Currently I have a predictive model, which predicts ETA flight times. Specifically, this is a regression that predicts the flight time that results from some features and the target variable:
Flight_duration = Arrival-time – Airborne time
This specified flight time is added to the Airborne timestamp to predict when it should be there.
Now I want to extend the model. It should no longer be predicted once at Airborne, but several times during the flight to improve the ETA forecast.
I got real-time flight data for that. There are now several lines with timestamp + coordinates for a specific flight where it is located.
The question I ask now is, how do I model exactly?
How can I use the coordinates optimally as a feature (as a geohash?)? Should I see this as a time series prediction? For example, I push the last t-3 features..for example geohash and how long the flight_duration to these points was in the model and forecast e.g. always the t + 1 flight duration.
Currently I use a Gradient Boosting model, which is quite good for a forecast at the Airborne time. For example, I have an RMSE of about 8 minutes at 12 hours flight time.
Do you have experience and can you share it with me?
machine-learning time-series
New contributor
$endgroup$
add a comment |
$begingroup$
Currently I have a predictive model, which predicts ETA flight times. Specifically, this is a regression that predicts the flight time that results from some features and the target variable:
Flight_duration = Arrival-time – Airborne time
This specified flight time is added to the Airborne timestamp to predict when it should be there.
Now I want to extend the model. It should no longer be predicted once at Airborne, but several times during the flight to improve the ETA forecast.
I got real-time flight data for that. There are now several lines with timestamp + coordinates for a specific flight where it is located.
The question I ask now is, how do I model exactly?
How can I use the coordinates optimally as a feature (as a geohash?)? Should I see this as a time series prediction? For example, I push the last t-3 features..for example geohash and how long the flight_duration to these points was in the model and forecast e.g. always the t + 1 flight duration.
Currently I use a Gradient Boosting model, which is quite good for a forecast at the Airborne time. For example, I have an RMSE of about 8 minutes at 12 hours flight time.
Do you have experience and can you share it with me?
machine-learning time-series
New contributor
$endgroup$
Currently I have a predictive model, which predicts ETA flight times. Specifically, this is a regression that predicts the flight time that results from some features and the target variable:
Flight_duration = Arrival-time – Airborne time
This specified flight time is added to the Airborne timestamp to predict when it should be there.
Now I want to extend the model. It should no longer be predicted once at Airborne, but several times during the flight to improve the ETA forecast.
I got real-time flight data for that. There are now several lines with timestamp + coordinates for a specific flight where it is located.
The question I ask now is, how do I model exactly?
How can I use the coordinates optimally as a feature (as a geohash?)? Should I see this as a time series prediction? For example, I push the last t-3 features..for example geohash and how long the flight_duration to these points was in the model and forecast e.g. always the t + 1 flight duration.
Currently I use a Gradient Boosting model, which is quite good for a forecast at the Airborne time. For example, I have an RMSE of about 8 minutes at 12 hours flight time.
Do you have experience and can you share it with me?
machine-learning time-series
machine-learning time-series
New contributor
New contributor
New contributor
asked 6 mins ago
OrgosMosOrgosMos
1
1
New contributor
New contributor
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "557"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
OrgosMos is a new contributor. Be nice, and check out our Code of Conduct.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f44372%2funique-eta-prediction-vs-continuous-eta-prediction%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
OrgosMos is a new contributor. Be nice, and check out our Code of Conduct.
OrgosMos is a new contributor. Be nice, and check out our Code of Conduct.
OrgosMos is a new contributor. Be nice, and check out our Code of Conduct.
OrgosMos is a new contributor. Be nice, and check out our Code of Conduct.
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f44372%2funique-eta-prediction-vs-continuous-eta-prediction%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown