Prediction Model
The problem:
There are historical daily data on the number of passengers.Transportation equipment needs a month in advance
Set up a timetable for the service staff.A prediction model.
This is the one that shows the forecast for only one day, not a month as needed.The task:
To add an existing model or to offer your own, which on historical data will learn and do
Passengers travel forecast for a month ahead.Precision of the forecast is 90-95% (In this model, with different settings, accuracy reaches 95%).The prediction schedule should continue the existing schedule with a red color.The existing disadvantages:
The model in the calculations uses the last 50 days??The ?- I would like to use the entire volume of data (here I may be wrong, in ML is not long).When formatting the graph appears Warning - to correct.When writing the code add comments so that when using it can be with understanding to change the parameters.Link to the model:
https://colab.research.google.com/drive/1PBhY35PIGBe_vh8783re44HAW19E-4ai?usp=sharing
Link to the file with data for the last year:
https://drive.google.com/file/d/1dZ1N1F9ZvbhGiCnOKYuMDU8EBRMSkLL-/view?usp=sharing
/
The problem:
There are historical daily data on the number of passengers travelling.Transport equipment is required for a month in advance.
A timetable for the service staff.There is a prediction model.
That shows the forecast only for one day, not for a month as required.The Task:
To submit an existing model or to propose its own, which on historical data will be trained and made.
Passengers travel forecast on the day by month ahead.Precision forecast 90-95% (In this model, with different settings, accuracy reaches 95%).The prediction chart must continue the existing chart with a red color.The existing shortcomings:
The model in calculations uses the last 50 days?The ?- I would like that all the data volume was used (here I can be wrong, in ML is not silenced).When the graph is formed, the warning appears - correct.When writing the code adds comments, so that when used it was possible with understanding to change the parameters.Reference to the model:
https://colab.research.google.com/drive/1PBhY35PIGBe_vh8783re44HAW19E-4ai?usp=sharing
Link to the file with data for the last year:
https://drive.google.com/file/d/1dZ1N1F9ZvbhGiCnOKYuMDU8EBRMSkLL-/view?usp=sharing
/
The problematic:
There is historical daily data on the number of passenger trips.Maintenance of equipment in transport requires a month in advance
draw up a schedule for the entry to work of service personnel.There is a prediction model.
which shows the forecast for only one day, and not for a month, as required.The task:
Refine the existing model or offer your own, which will train on historical data and make
Forecast of passenger trips by days for a month in advanceThe forecast accuracy is 90-95% (For this model, with different settings, the accuracy reaches 95%).Prediction chart should continue the existing chart in red.The existing shortcomings:
Does the model use the last 50 days in its calculations??The ?I would like the entire amount of data to be used (I could be wrong here, it's not strong in ML).Warning appears when the chart is being formed - fix it.When writing the code, add comments so that when using it I can change the parameters with understanding.Model of Reference:
https://colab.research.google.com/drive/1PBhY35PIGBe_vh8783re44HAW19E-4ai?usp=sharing
Link to file with data for the last year:
https://drive.google.com/file/d/1dZ1N1F9ZvbhGiCnOKYuMDU8EBRMSkLL-/view?usp=sharing
Варіант, коли за основу взято "one step prediction" і на його основі робиться 30 step prediction - не підходить. Такий варіант випробуваний і він дає помилкові результати.
/
Вариант, когда берётся "one step prediction" о на его основе делается 30 step prediction - не подходит. Такой вариант опробован и он даёт ошибочные результаты.
/
The option when "one step prediction" is taken as a basis and 30 step prediction is made on its basis is not suitable. This option has been tested and gives erroneous results.
X_FUTURE = 30
predictions = np.array([])
last = x_test[-1]
for i in range(X_FUTURE):
curr_prediction = model.predict(np.array([last]))
last = np.concatenate([last[1:], curr_prediction])
predictions = np.concatenate([predictions, curr_prediction[0]])
predictions = scaler.inverse_transform([predictions])[0]
print(predictions)
import datetime
from datetime import timedelta
dicts = []
curr_date = data.index[-1]
for i in range(X_FUTURE):
curr_date = curr_date + timedelta(days=1)
dicts.append({'Predictions':predictions[i], "Date": curr_date})
new_data = pd.DataFrame(dicts).set_index("Date")
train = data
plt.figure(figsize=(22,11))
plt.title('Prediction model')
plt.xlabel('Date', fontsize=18)
plt.ylabel('Pass trips (units)', fontsize=18)
plt.plot(train['Pass'])
plt.plot(new_data['Predictions'])
plt.legend(['Train', 'Predictions'], loc='lower left')
plt.show()
Client's review of cooperation with freelancer
Prediction ModelThank you ! Everything is done with understanding. Everything is good!
Freelancer's review of cooperation with Viktor Chekin
Prediction ModelИдеал заказчика!
Мне просто дали задание, я его выполнил.
Чётко поставил цель, сроки, цену и т.д.
![]()
-
Добрый вечер.
Интересуют ориентировочные сроки.
С уважением, Сергей
-
И да, использование всего исторического периода - плохая мысль.
Обычно используют либо те же периоды предыдущих лет для учета сезонности, либо последние данные с фильтром затухания значимости (чем дальше, тем меньше данные влияют на предсказания)
-
Current freelance projects in the category AI & Machine Learning
Need an N8N expert for automation and building a system for TikTok farms.
639 USD
My marketing team and I are testing quick ideas for applications. We are looking for a person on a permanent basis to automate processes in N8N, specifically to build a system from scratch and then maintain its functionality. I would appreciate your response! *Unfortunately, I… AI & Machine Learning, System & Network Administration ∙ 10 hours 36 minutes back ∙ 16 proposals |
Development of software with AIIt is necessary to develop software for automatic detection, capturing, and tracking of an object using a video camera and a rotating mechanism.Output data: Video camera with optics. Rotating device on two axes (azimuth/elevation angle). Servomotors controlled via Modbus… AI & Machine Learning, Python ∙ 17 hours 40 minutes back ∙ 12 proposals |
Automation of processes through API and PythonBelow I described the current process and the result I would like to achieve. I also attach files of the real process to better understand how it looks in reality Current process Currently, the entire process is performed manually: uploading/downloading files, transferring… AI & Machine Learning, Python ∙ 22 hours 45 minutes back ∙ 42 proposals |
Finding and Deploying the Best Projects for 4 Mac Mini M4 Machines
229 USD
Finding and Deploying the Best Projects for 4 Mac Mini M4 Machines Hello, I am looking for an experienced technical freelancer who understands Mac Mini M4 hardware, DePIN, blockchain nodes, AI inference, automation systems, Docker, and server monitoring. I currently have 4… AI & Machine Learning, Cryptocurrency & Blockchain ∙ 1 day 10 hours back ∙ 8 proposals |
Development of an AI consultant for a work visa verification website (WordPress)Development of an AI Consultant for a Work Visa Check Website (WordPress) About the Project An English-language website is being developed for the preliminary check of eligibility for a work visa in Israel. An AI consultant in the format of an online chat is needed to assist… AI & Machine Learning, Bot Development ∙ 1 day 17 hours back ∙ 35 proposals |