Projects | Aliaksandr Nekrashevich

Sleep Study with Fitness Tracker

Tue, 10 Oct 2023 00:00:00 +0000

A data-science study of personal sleep problems based on the data collected from the Fitbit fitness tracker using semi-advanced Time Series forecasting.

Revenue Management System Prototype for a Private Golf Hotel Resort

Wed, 26 Oct 2022 00:00:00 +0000

An approach based on the randomized linear programming for estimating bid prices was successfully applied with approximately a 5% revenue increase. The source code is in a private repository, but I can show the non-NDA-protected components during personal communication.

Prototype for Sea Freight Revenue Management System

Sun, 10 Oct 2021 00:00:00 +0000

The project is scalable, accounts for uncertainty, makes a profit from empty container transportation, and covers more business lines together than the previous implementations. Lagrangian-Relaxation based framework was extended for mixed event types and two types of constraints of different structures. The source code is in a private repository, but I can show the code during personal communication.

Client Behavior on Car Credit Payments at a Bank in Eastern Europe

Sat, 26 Oct 2019 00:00:00 +0000

This project addresses the problem of issuing a credit loan for the purpose of purchasing a car. The dataset was openly presented in a competition in which the author had the opportunity to participate at one of the Belarusian banks (more precisely, BNB-bank or Belaruski Narodny Bank). The goal is to understand the client’s behaviour and repayment policies based on their internal features.

Although credit scoring is working, clients behave differently. The natural question is then how to use this variability in client behaviour to make the bank better. Note that the financial atmosphere and economic ecology are very risky in Belarus, which adds additional challenges to the problem. The initial draft version was implemented at the competition with contributions from other team members. The project was afterwards re-implemented and enhanced during my studies at the MGMT-962 course at the Smith School of Business.

Esicup Challenge 2015

Mon, 01 Jun 2015 00:00:00 +0000

The project was motivated by the international contest about the best packing for a real-life logistic problem from the car manufacturer RENAULT. Our team has passed qualification with 4th place, and got 5th place on Instances A, 6th place on Instances B and 5th place on Instances X.

Project Data:

Qualifier Code:

Final Code: