Tag Archives: philgeps

Home › philgeps

Predicting Public Procurement Irregularities in the COVID-19 Response of Local Government Units (LGUs) in the Philippines

Authors: Barajas, J.R., Aspra, N., Gealone, P.J., Lucero, A., Padua, O., Ramos, M.

Motivated by ensuring transparency, fairness, and efficiency in public procurement at the time of the COVID-19 pandemic, a team of engineers and faculty from Bicol Region (Region 5) in the Philippines collected, digitized, and analyzed public procurement data to inform the COVID-19 response of select Local Governments in the country.

Highlights of the Report:

• On average, only 2 out of 10 LGU contracts have been awarded in
2020.

• For every Php1 spent, approximately Php1 remains unspent in
the procurement of goods and services made by LGUs.

• A total of Php481 billion were distributed across all LGUs in the country
for 2020 but only 10% of this budget was allocated for the procurement
of drugs and medicines. 40% of this budget went to construction
projects.

• Excluding LGU contracts not posted in the PhilGEPS website, only Php10
billion (2.16% of the total LGU budget) was allocated for COVID-
19 related contracts.

• An equivalent amount of Php720 million was potentially lost from 786
LGU contracts flagged as irregular.

• Audit findings for LGUs were primarily centered on directing accountable
officers to comply to documentary requirements mandated by existing
circulars, memorandums, and Philippine laws.

• A logistic regression model with an accuracy of 91.29% was developed
to identify contracts that are potentially irregular.

Short Summary of the Report:

From examination of 296,220 local government unit contracts, this project was able to develop a logistic regression model capable of predicting potentially irregular LGU contracts posted on the PhilGEPS website for the fiscal year 2020 at an accuracy of 91.29%. Validation of the model using metrics derived from the confusion matrix revealed that the developed model had a recall score of 1.0 and a precision score of 0.029. While the precision of the model may be
low, the high recall score is deemed more important in this use-case since it would be more costly for an LGU to miss out on irregular contracts. Overall, the developed prediction model is seen to be highly beneficial as a decision
support tool for LGUs since this could potentially narrow down the number of awarded LGU contracts to be legally reviewed resulting in a faster turnover of review cycles conducted within a given fiscal year.

The team’s collected datasets are available for download in the OCDex open data portal, attribution to the authors and contributors is required for use.

DOWNLOAD FULL REPORT HERE:

Loader Loading…
EAD Logo Taking too long?

Reload Reload document
| Open Open in new tab

Are you interested in this report? Do reach out to us at learning@layertechlab.com so that we can directly connect you with the authors, as well as the documentations they submitted.

Procurement Business Intelligence Workshop for Businesses

Comment

To Bid or Not to Bid? That is the Question!

Layertech Labs led the Procurement Data Analytics and Business Intelligence Workshop for Business Owners (and Bankers) in Albay.

Businesses were introduced WHERE to get official Philippine procurement data, HOW to process the data with both technical and non-technical tools, HOW to spot malicious/exaggerated graphs and data, as well as a short introduction how to use procurement business intelligence to inform business decisions and bidding strategies.

Businesses in Albay, some are owners, and C-executives themselves, attended the hands-on workshop at The Oriental Hotel Legazpi, Albay, Philippines.

At the end of the workshop, the participants shared their outputs and insights on Philippine Procurement, and how they can use Business Intelligence from PhilGEPS data to influence their Bidding Strategies.

The workshop was made possible thanks to Hivos, under the Open Contracting Programme, and the Albay Chamber of Commerce and Industry.

PhilGEPS Dataset Columns to OCDS Mapping Guide

Comment

PhilGEPS releases Philippine procurement datasets in excel format. These are downloadable in their official PHILGEPS OPEN DATA PORTAL.

Below is a mapping Layertech and Partners in Legazpi made to convert PH-based procurement datasets to OCDS format. This is being used by partner researchers, developers, and students to create localized procurement monitoring tools. 

 
This work is licensed under a Creative Commons Attribution 3.0 Unported License.

Download [17.33 KB]

Layertech Leads Data Scraping Session using R and R Studio

Comment

Supported by Hivos, Layertech lead a data scraping session using R and R Studio, using official Philippine Procurement Datasets found in Philgeps.gov.ph’s Open Data Portal.

The session attendees were faculty members of Bicol University College of Science IT Department, and faculty and graduating students of Southern Luzon Technological College Foundation, Inc.

While procurement datasets are available in open data formats, the large PhilGEPS datasets still need to be pre-processed, filtered, visualized and analyzed. Only then can researchers, advocates, and concerned citizens draw useful insights to aid them in their advocacy and decision making.

What’s the objective?

Layertech and partners advocate for #DataDrivenGovernance. We aim to encourage researchers to study and innovate on government procurement. For them to do that, they must be equipped with the necessary skills and tools to draw insights from procurement information that is available.

For this first session, the academe was specifically invited because the team also needs to get their insights, comments and suggestions about the training design, in order to improve the next tech training sessions to come.

The team and partners will soon be deploying training sessions for young researchers, students, innovators, and faculty, on various topics such as:

Data Science
Data Analytics
Data Visualization
Python Programming
Machine Learning
Cybersecurity
Data Privacy

What are the results?

For the first training session with R, the participants were able to publish a total of 13 datasets (downloadable HERE, in our Open Data Portal) under various categories such as Health, Local Government, and Education.

The participants also actively presented their outputs and how these cleaned datasets can help increase transparency and efficiency in public procurement in the Philippines.

Want to know more about HOW to filter Philgeps datasets? Here’s a quick, general guide HERE.

Keep on visiting our “References” section for more procurement and data scraping, visualization, and analytics guides!

How to filter PhilGEPS data with R and R Studio

Comment

PRE-REQUISITE: You must have R and R Studio BOTH installed in your computer. If you don’t, download the installers on the following links and install them to your computer!

R - https://cran.stat.upd.edu.ph
R Studio - https://www.rstudio.com/

Once your have R and R Studio both up and running, we can now proceed to the filtering!

STEP 1 – Go to www.PHILGEPS.GOV.PH and go to the “Open Data” Section. Try downloading the excel files they have over there. We often use the datasets of the Invitations to Bid and Notices of Award.

STEP 2 – The files are in XLSX format. We prefer to export them to CSV because its easier to ingest and because csv is #OPENData format. So yeah. ALSO! Make sure that the rows do not have blanks on the top. The top row will automatically become the ‘header’ once it is ingested in R Studio so make sure the top row is the row that contains the column labels (except if you you key in more lines of course, so let’s keep it simple).

STEP 3 – Ingest the CSV file in RStudio as a dataframe. Normally, we do the following:

DATA_FRAME_NAME = read.csv("PATH/TO/FILE.csv")

STEP 4 – Now that you have a dataframe in R, you can now perform basic operations on it. For example, we normally filter the name of the agency that we are interested in. For example we do something like:

DATA_FRAME_NAME_NEW <- subset(DATA_FRAME_NAME, ColumnName==”ParameterHere”)
example:

JUL_SEP_2018_sub <- subset(JUL_SEP_2018, Organization.Name=="DEPARTMENT OF HEALTH - REGIONAL OFFICE V")

We now have a NEW Dataframe, with only the data from Department of Health Regional Office 5. 🙂 But remember! The stings are case sensitive so you have to make sure that you are inputting the correct name. You can do a quick search in the raw table and copy-paste the parameter just to be sure 🙂

You can perform several other operations on the dataframe! You can remove columns, count occurrences, join two or more dataframes, and more. To find out more operations, you can google for “R Cheatsheets” for commands and examples.

STEP 5 – If you are satisfied with your final dataframe, we request that you save it as a CSV file through the following commands: 

write.csv(DATA_FRAME_NAME, file=”PREFERRED_FILE_NAME.csv”

This is because, chances are, some other researcher, or concerned citizen (who isn’t familiar with R) would need the dataset you just made. Sharing is Caring! 🙂

STEP 6 – Finally, you can share your cleaned datasets in our repository! We will make sure to credit you with your preferred name/nickname. Send us your dataset and we will upload it for you (for now. We are working on a way so that you can upload by yourself :) )

All data uploaded will be available as open datasets. They are free for all, so that we can encourage more and more researchers, advocates, to use data and be data-driven in their decision making.

Thank you very much! For more information, kindly email support@layertechlab.com. From time to time, we conduct hands-on trainings! Please let us know if you are interested!