Predicting Product Uptake Using Bass, Gompertz, and Logistic Diffusion Models: Application to a Broadband Product
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.
Bibliographic record
Abstract
In today’s competitive environment, broadband companies innovate to stay competitive, retain existing customers, and attract new customers. A recent innovative product in this industry is the deployment of the gigabit Internet service over fiber optic networks as a solution to the growing bandwidth demands from consumers. One determinant of the decision to deploy such product is the expectation of a positive return on investment (ROI) determined among others by the penetration or take rate of the product or service. Like any product, the adoption of the gigabit Internet is influenced by the reaction of customers to this innovation. Some customers are early adopters of the product while others might not be interested in higher bandwidth Internet connections or will simply adopt the product at a later time. The purpose of this paper was to identify a model that best predicts future trends in the uptake of the gigabit Internet product over fiber-to-the home (FTTH). To that effect, this study implemented three different models: Bass, Gompertz, and logistic diffusion models; analyzed their predictive abilities; and determined the best fit model in a FTTH brownfield scenario. The data used for the study were split into two sets: the first or training set was used to create the models and the second was used to validate their predicting abilities. The data analysis used the ordinary least squares (OLS) method to select the best fit model. The results suggested that while Gompertz best fitted the training data, Bass had a better forecasting power. In other words, the Bass diffusion model was best at forecasting future uptake of the gigabit Internet service, while Logistic optimistically forecasted above the take rate and Gompertz pessimistically forecasted below. These findings present various implications for researchers and practicians. For example, future research could replicate the study for different industries and products, while practicians could anticipate realistic financial results from the implementation of the findings.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.018 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it