Freelancer标志它是如何运作的 浏览工作
登录 注册
发布项目
探索
Algorithm
Machine Learning (ML)
Matlab and Mathematica
Scientific Research
Statistics
个人资料封面照片
您正在关注
关注用户错误。
该用户不允许他人关注他们。
您已经关注了这个用户。
您的会员计划仅允许0个关注。升级在此。
成功取消关注
取消关注用户错误
您已成功推荐
推荐用户错误。
出问题了，请刷新页面并重新尝试。
电子邮箱已成功验证。
用户头像
$15 USD / 小时
TAJIKISTAN的国旗
dushanbe, tajikistan
$15 USD / 小时
目前这里是12:59 上午
七月 18, 2023已加入
0 推荐

Ilyas V.

@IlyasVarsh

 0.0 (0条评论)
0.0
0.0
0%
0%
$15 USD / 小时
TAJIKISTAN的国旗
dushanbe, tajikistan
$15 USD / 小时
不适用
工作已完成
不适用
在预算内
不适用
按时
不适用
重复雇用率

Data scientist, Scientific researcher

Stack: Python & ML libs, Matlab Industry: Information & measurement, Fintech, Computer science Skills: ML, AI, Deep Learning, NN, Mathematic, Statistic, Data analysis, Data processing, Data preprocessing, Visualization, Algorithms
Freelancer Matlab and Mathematica Engineers Tajikistan
查看所有Matlab and Mathematica Engineers在Tajikistan

联系Ilyas V.询问您的工作详情

登录并通过聊天讨论所有细节。

文件夹

11178028
Dynamic pricing is frequently used in online marketplaces, ticket sales, and booking systems. The commercial principles of dynamic pricing systems are often kept secret; however, their application causes complex changes in human behavior. Thus, a scientific tool is needed to evaluate and predict the impact of dynamic pricing strategies. Publications in the field lack a common quality evaluation methodology, public data, and source code, making them difficult to reproduce. In this paper, a data-driven method, DPRank, for evaluating dynamic pricing systems is proposed. DPRank first builds a surrogate price elasticity of demand model using public data generated by a hidden dynamic pricing model, and then applies the surrogate model to build an exposed dynamic pricing model. The hidden and exposed dynamic pricing models were then systematically compared in terms of quality using a Monte Carlo simulation in terms of a company’s revenue. The effectiveness of the proposed method was tested on
Dynamic Pricing for the Open Online Ticket System: A Surroga
11178025
Dynamic pricing is frequently used in online marketplaces, ticket sales, and booking systems. The commercial principles of dynamic pricing systems are often kept secret; however, their application causes complex changes in human behavior. Thus, a scientific tool is needed to evaluate and predict the impact of dynamic pricing strategies. Publications in the field lack a common quality evaluation methodology, public data, and source code, making them difficult to reproduce. In this paper, a data-driven method, DPRank, for evaluating dynamic pricing systems is proposed. DPRank first builds a surrogate price elasticity of demand model using public data generated by a hidden dynamic pricing model, and then applies the surrogate model to build an exposed dynamic pricing model. The hidden and exposed dynamic pricing models were then systematically compared in terms of quality using a Monte Carlo simulation in terms of a company’s revenue. The effectiveness of the proposed method was tested on
Dynamic Pricing for the Open Online Ticket System: A Surroga
11178021
This study proposes a solution to the problem of railway demand forecasting on open data of a passenger railway company and search engines. A time series of web search queries is used as a predictor, and demand time series for train tickets is used as a target variable. The predictor is taken with a lag corresponding to the best correlation with the demand series. The LSTM, MV-LSTM, ARIMA, SARIMA, ARIMAX and SARIMAX models are used for forecasting. ARIMA-based models are used in 39 and 1 day forecasting experiments. SARIMAX model showed slightly better results in 1-day prediction experiments, however, the MV-LSTM model significantly improved the metrics due to the use of a predictor. The results of many experiments show the usefulness of using web search queries as a predictor for predicting passenger demand for rail tickets, the quality of the best model improved to 1.43 percentage points by MAPE and 76 by RMSE which is measured in terms of sold tickets, relative to models trained wit
Forecasting railway ticket demand with search query open dat
11178017
This study proposes a solution to the problem of railway demand forecasting on open data of a passenger railway company and search engines. A time series of web search queries is used as a predictor, and demand time series for train tickets is used as a target variable. The predictor is taken with a lag corresponding to the best correlation with the demand series. The LSTM, MV-LSTM, ARIMA, SARIMA, ARIMAX and SARIMAX models are used for forecasting. ARIMA-based models are used in 39 and 1 day forecasting experiments. SARIMAX model showed slightly better results in 1-day prediction experiments, however, the MV-LSTM model significantly improved the metrics due to the use of a predictor. The results of many experiments show the usefulness of using web search queries as a predictor for predicting passenger demand for rail tickets, the quality of the best model improved to 1.43 percentage points by MAPE and 76 by RMSE which is measured in terms of sold tickets, relative to models trained wit
Forecasting railway ticket demand with search query open dat
11178028
Dynamic pricing is frequently used in online marketplaces, ticket sales, and booking systems. The commercial principles of dynamic pricing systems are often kept secret; however, their application causes complex changes in human behavior. Thus, a scientific tool is needed to evaluate and predict the impact of dynamic pricing strategies. Publications in the field lack a common quality evaluation methodology, public data, and source code, making them difficult to reproduce. In this paper, a data-driven method, DPRank, for evaluating dynamic pricing systems is proposed. DPRank first builds a surrogate price elasticity of demand model using public data generated by a hidden dynamic pricing model, and then applies the surrogate model to build an exposed dynamic pricing model. The hidden and exposed dynamic pricing models were then systematically compared in terms of quality using a Monte Carlo simulation in terms of a company’s revenue. The effectiveness of the proposed method was tested on
Dynamic Pricing for the Open Online Ticket System: A Surroga
11178025
Dynamic pricing is frequently used in online marketplaces, ticket sales, and booking systems. The commercial principles of dynamic pricing systems are often kept secret; however, their application causes complex changes in human behavior. Thus, a scientific tool is needed to evaluate and predict the impact of dynamic pricing strategies. Publications in the field lack a common quality evaluation methodology, public data, and source code, making them difficult to reproduce. In this paper, a data-driven method, DPRank, for evaluating dynamic pricing systems is proposed. DPRank first builds a surrogate price elasticity of demand model using public data generated by a hidden dynamic pricing model, and then applies the surrogate model to build an exposed dynamic pricing model. The hidden and exposed dynamic pricing models were then systematically compared in terms of quality using a Monte Carlo simulation in terms of a company’s revenue. The effectiveness of the proposed method was tested on
Dynamic Pricing for the Open Online Ticket System: A Surroga
11178021
This study proposes a solution to the problem of railway demand forecasting on open data of a passenger railway company and search engines. A time series of web search queries is used as a predictor, and demand time series for train tickets is used as a target variable. The predictor is taken with a lag corresponding to the best correlation with the demand series. The LSTM, MV-LSTM, ARIMA, SARIMA, ARIMAX and SARIMAX models are used for forecasting. ARIMA-based models are used in 39 and 1 day forecasting experiments. SARIMAX model showed slightly better results in 1-day prediction experiments, however, the MV-LSTM model significantly improved the metrics due to the use of a predictor. The results of many experiments show the usefulness of using web search queries as a predictor for predicting passenger demand for rail tickets, the quality of the best model improved to 1.43 percentage points by MAPE and 76 by RMSE which is measured in terms of sold tickets, relative to models trained wit
Forecasting railway ticket demand with search query open dat
11178017
This study proposes a solution to the problem of railway demand forecasting on open data of a passenger railway company and search engines. A time series of web search queries is used as a predictor, and demand time series for train tickets is used as a target variable. The predictor is taken with a lag corresponding to the best correlation with the demand series. The LSTM, MV-LSTM, ARIMA, SARIMA, ARIMAX and SARIMAX models are used for forecasting. ARIMA-based models are used in 39 and 1 day forecasting experiments. SARIMAX model showed slightly better results in 1-day prediction experiments, however, the MV-LSTM model significantly improved the metrics due to the use of a predictor. The results of many experiments show the usefulness of using web search queries as a predictor for predicting passenger demand for rail tickets, the quality of the best model improved to 1.43 percentage points by MAPE and 76 by RMSE which is measured in terms of sold tickets, relative to models trained wit
Forecasting railway ticket demand with search query open dat

评论

变更已保存
这里没有评论！

经验

Scientific Researcher

ITMO University
12月 2021 - 12月 2022 (1 年)
Stack: Python and Data Science libraries (Numpy, Pandas, SciPy, TensorFlow, SciKit-Learn, Seaborn et al.), LaTeX. Industry: FinTech, Computer science Skills: Machine Learning · Deep Learning · Python (Programming Language) · Data Analysis · Optimization Algorithms

Assistant of the Department of Information and Measuring Systems and Technologies (ETU "LETI")

Saint Petersburg State Electrotechnical University "LETI"​
9月 2015 - 6月 2022 (6 年, 9 个月)
Scientific and educational activities. Scientific: development and research of multichannel information-measuring systems. Educational: Metrology, Computer technologies in instrument making, Theoretical foundations of information and measuring equipment, Adaptive information and measuring systems, Bachelor's scientific director. Skills: Research Skills · Mentoring · University Teaching · Publications · Presentation Skills

Middle Software Developer

Saint Petersburg State Electrotechnical University "LETI"​
3月 2021 - 12月 2021 (9 个月, 1 天)
Development of software for the automatic control system, collection, processing and analysis of measurement data. Skills: Machine Learning · Python (Programming Language) · Statistical Data Analysis · Data Analysis · Error Analysis

教育

PhD (Russian PhD)

Sankt-Peterburgskij Gosudarstvennyj Elektrotehniceskij Universitet 'LETI', Russian Federation 2015 - 2021
(6 年)

Researcher. Lecturer-Researcher.

Sankt-Peterburgskij Gosudarstvennyj Elektrotehniceskij Universitet 'LETI', Russian Federation 2015 - 2019
(4 年)

Master

Sankt-Peterburgskij Gosudarstvennyj Elektrotehniceskij Universitet 'LETI', Russian Federation 2013 - 2015
(2 年)

资质

ArcGIS: Tools, functionality, and execution of analysis

Saint Petersburg State Electrotechnical University "LETI"​
2020
Data analysis in geographic information systems.

Frontiers of applied artificial intelligence: industrial, economics, education

ITMO University
2021
The school will be devoted to the development of promising AI technologies that form the methodological and algorithmic foundations of strong AI, which provides decision support in situations that exceed the cognitive abilities of an expert in complexity.

出版物

Optimal Design of the Structure of an Adaptive Information-Measuring System

IEEE
The functioning of complex technical objects involves the use of information-measuring systems to obtain information about the environment and the state of devices within the system itself. At the same time, to prevent emergency and pre-emergency situations, it is important to receive timely information about the discrete state of the object, for example, information about the presence of sand in the flow of the produced hydrocarbons...

Dynamic Pricing for the Open Online Ticket System: A Surrogate Modeling Approach

Smart Cities
Dynamic pricing is frequently used in online marketplaces, ticket sales, and booking systems. The commercial principles of dynamic pricing systems are often kept secret; however, their application causes complex changes in human behavior. Thus, a scientific tool is needed to evaluate and predict the impact of dynamic pricing strategies. Publications in the field lack a common quality evaluation methodology, public data, and source code, making them difficult to reproduce.

Forecasting railway ticket demand with search query open data

Procedia Computer Science
This study proposes a solution to the problem of railway demand forecasting on open data of a passenger railway company and search engines. A time series of web search queries is used as a predictor, and demand time series for train tickets is used as a target variable. The predictor is taken with a lag corresponding to the best correlation with the demand series.

联系Ilyas V.询问您的工作详情

登录并通过聊天讨论所有细节。

认证

优选威客
身份已验证
支付已验证
电话已验证
邮箱已验证
Facebook已关联

顶级技能

Matlab and Mathematica
Scientific Research
Algorithm
Statistics
Machine Learning (ML)

浏览相似威客

Matlab and Mathematica Engineers in Tajikistan
Matlab and Mathematica Engineers
Scientific Researchers
Algorithm Experts

浏览相似作品

Matlab and Mathematica
Scientific Research
Algorithm
Statistics
之前的用户 下一个用户
邀请已发送成功！
谢谢！我们已通过电子邮件向您发送了索取免费积分的链接。
发送电子邮件时出现问题。请再试一次。
Freelancer标志 Hong Kong / 中文(简体) 帮助和支持 威客分类项目竞赛威客企业会员优选威客计划项目管理本地工作Photo Anywhere 作品展示开发人员API获得认证桌面APP 关于关于我们如何运作安全投资方网站地图故事消息团队奖励新闻发布职业 条款隐私政策条款和条件版权政策行为准则费用及收费合伙人Escrow.comLoadshiftWarrior Forum 应用程序苹果APP商城图标Google Play标志
复制到剪切板失败，请修改权限后重试。
复制到剪贴板。
已注册用户 发布工作总数
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2024 Freelancer Technology Pty Limited (ACN 142 189 759)
加载预览
授予地理位置权限。
您的登录会话已过期而且您已经登出，请再次登录。