Price discovery algorithm for free-form PHILGEPS dataset

Authors

  • Joseph Roel Jaro Mabajen ⋅ PH National Institute of Physics, University of the Philippines Diliman
  • May T. Lim ⋅ PH National Institute of Physics, University of the Philippines Diliman

Abstract

PHILGEPS is the official online platform used in government procurement of products and services. In this work, we aim to perform price discovery on the products listed in the free-form PHILGEPS 2016 procurement report. The text listings were first lemmatized to determine product keywords. Afterwards, product price distributions were generated by kernel density estimation in conjunction with two-sample Kolmogorov-Smirnov test. Lastly, keywords were clustered into three groups based on their threshold bandwidth hth. It was found that general product terms cluster together, with the specific product identifiers having bandwidths between 0.25 and 1.50.

Downloads

Issue

Article ID

SPP-2018-1B-05

Section

Complex Systems and Data Analytics

Published

2018-05-23

How to Cite

[1]
JRJ Mabajen and MT Lim, Price discovery algorithm for free-form PHILGEPS dataset, Proceedings of the Samahang Pisika ng Pilipinas 36, SPP-2018-1B-05 (2018). URL: https://proceedings.spp-online.org/article/view/SPP-2018-1B-05.