Projects in Sustainable Cities

Sustainable Data-Driven Public Transport Systems

Project members:

  • Institute for Computational Intelligence (ICI), Universidad Privada Boliviana
  • Centro de Investigaciones Sociales (CIS), Vicepresidencia del Estado Plurinacional de Bolivia

Project duration: March 2018 – March 2019

Mobility in La Paz is dominated by the so-called informal public transport sector. Transport routes and services are determined by various privately run, often competing syndicates. Vehicles are purchased by individual drivers and the syndicates do not maintain public infrastructure such as bus stops. This results in large fleets of low capacity vehicles competing over passengers and often causing traffic disruptions as well as dangerous traffic conditions. As the population and urban area of La Paz and El Alto are rapidly increasing the organization of the informal transport system increasingly poses a problem to urban development and public health. In this project we seek to analyze the current public transport landscape and to develop intelligent strategies for the improvement of the public transport sector.


Projects in Industry & Innovation

Data-Driven & Emerging Technologies in Supply Chain Management

Project duration: Nov 2018 – ongoing


The Institute for Computational Intelligence, through UPB, is a member of the MIT Global SCALE (Supply Chain and Logistics Excellence) network. With our expertise in computational intelligence we are the regional lead for research projects under the umbrella of “Data-Driven & Emerging Technologies” (DD&ET). As the lead on DD&ET research we are developing research projects and are coordinating collaborations within the Latin American SCALE network.

Read more at: Data-Driven & Emerging Technologies


Demand Forecasting with Recurrent Neural Networks

Project duration: July 2018 – June 2019

In production and operational management demand forecasting is an important method as it helps to develop better approximations of future operations under the presence of uncertainty. Forecasting extracts mathematical relations from past data that can be used to inform future decision making. In supply chain management, efficient coordination of resource acquisition, production and warehousing strongly depends on accurately predicting future product demand in particular and market dynamics in general. Accurate demand forecasting therefore reduces investment risks in uncertain environments. The challenges of demand forecasting lie in the complexity of demand dynamics. We investigate the application of reservoir computing (RC) to product demand forecasting. RC utilizes a randomly initialized recurrent neural network that implements finite memory and generalization. Under these conditions it should be sufficient to reduce training complexity to only a single linear output layer and achieve accurate forecasting results. The output layer is therefore able to derive a simple linear relationship between the input data and its projection into a higher-dimensional feature space.


Slotting Heuristics and Order-picking Efficiency in Warehouse Operations

Project duration: July 2018 – December 2018

Order picking, the process of collecting and sorting a set of products according to customer orders, is the main cost driver in warehouse operations. Order picking consists of travel between product locations, retrieval of the specific stock keeping unit (SKU), and sorting of SKUs according to customer orders. Travel is estimated to contribute approximately 50% of the total order picking costs. Due to daily, weekly, monthly, seasonal and yearly demand fluctuations, order picking efficiency can vary greatly under time-varying order patterns. We investigate the time-dependent dynamics of order picking efficiency in relation to different slotting strategies to understand resilience to order fluctuations and their impact on picking efficiency.