Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Dynamic Repositioning to Reduce Lost Demand in Bike Sharing Systems
Authors: Supriyo Ghosh, Pradeep Varakantham, Yossiri Adulyasak, Patrick Jaillet
JAIR 2017 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we demonstrate the utility of our approach by comparing against two benchmark approaches on two real-world data sets of bike sharing systems. These approaches are evaluated using a simulation where the movements of customers are generated from real-world data sets. |
| Researcher Affiliation | Academia | Supriyo Ghosh EMAIL Pradeep Varakantham EMAIL School of Information Systems Singapore Management University, Singapore 178902 Yossiri Adulyasak EMAIL Department of Logistics and Operations Management HEC Montr eal, 3000 chemin de la Cˆote-Sainte-Catherine Montr eal, H3T 2A7, Canada Patrick Jaillet EMAIL Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology, Cambridge Massachusetts 02139, USA |
| Pseudocode | Yes | Algorithm 1 : Solve LDD(drrp) Initialize: α0, it 0 repeat o1, x, y , y+ SOLVEREDEPLOY(αit, drrp) o2, z SOLVEROUTING(αit, drrp) αit+1 s,t,v αit s,t,v + γ (y+,t s,v + y ,t s,v C v P i zt s,i,v) + p, xp, y p , y+ p EXTRACTPRIMAL (Z, drrp) it it + 1 until p (o1 + o2) δ return p, xp, y+ p , y p , z |
| Open Source Code | No | The paper does not provide a direct link to a source code repository, explicitly state that code is released, or mention code in supplementary materials for the methodology described. |
| Open Datasets | Yes | We employ data sets of two leading bike sharing systems in US11, namely, Capital Bikeshare (Washington, DC) and Hubway (Boston, MA)... 11. The data is taken from Capital Bikeshare [http://capitalbikeshare.com/system-data] and Hubway BSS [http://hubwaydatachallenge.org/trip-history-data]. |
| Dataset Splits | No | The paper refers to using a "training data set" and a "test data set" but does not specify the explicit proportions, methods (e.g., random split, stratified), or sample counts for these splits. It generally discusses evaluating solutions on a simulation using the test data set and sometimes deriving solutions from the entire dataset. |
| Hardware Specification | Yes | All the linear optimisation models were solved using IBM ILOG CPLEX Optimisation Studio V12.5 incorporated within python code on a 3.2 GHz Intel Core i5 machine. |
| Software Dependencies | Yes | All the linear optimisation models were solved using IBM ILOG CPLEX Optimisation Studio V12.5 incorporated within python code on a 3.2 GHz Intel Core i5 machine. |
| Experiment Setup | Yes | The planning horizon for our approach is 38 time steps (30 minute intervals during the working hours from 5AM-12AM) for the entire day and 14 time steps for the peak period (30 minute intervals during the morning working hours from 5AM-12PM). ... we employ 5 vehicles for the experiments on Capital Bikeshare data set and 3 vehicles for the experiments on Hubway data set. ... we choose 30 minute as the default setting for the duration of time step. |