MétaCan
Menu
Back to cohort
Record W4224238684 · doi:10.1117/12.2628088

Predicting Google Play Store Apps installations with linear regression and XGBoost

2022· article· en· W4224238684 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueInternational Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2021) · 2022
Typearticle
Languageen
FieldEngineering
TopicGreen IT and Sustainability
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsComputer scienceSet (abstract data type)Mobile appsWorld Wide WebApp storeMobile devicePredictive modellingRegression analysisData scienceMachine learning

Abstract

fetched live from OpenAlex

Mobile phones and other portable electronic devices have taken an important role in our daily lives, and people’s expectations of the functionalities of such devices are constantly changing. For the mobile application marketplace to successfully meet the customer requirements, app developers must understand the market trends and users' interests. One way to evaluate the extent of success of an app is its amount of installations. With most existing model forecasts, app installs as a time series of past installation amounts. This article analyses the known features of applications such as category, rating, content rating, genre, etc., with linear regression and Extreme Gradient Boost to extract the relationship between app features and installations. The dataset used for training the models is ‘Google Play Store Apps’ from the world’s largest data science community, Kaggle. Furthermore, the performance of each model is demonstrated and compared with predictions on a testing set. The article describes the details in data processing, model training, and predicting. The results exhibit a strong relationship between several features, including date of last update, genre, and amount of reviews with app installations, and consequently provide a reference for app developers to understand the factors that impact the install amounts.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.941
Threshold uncertainty score0.715

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.018
GPT teacher head0.257
Teacher spread0.239 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it