A Machine Learning Approach to Suggest Ideal Geographical Location for New Restaurant Establishment

Shihab, Ibne Farabi; Oishi, Maliha Moonwara; Islam, Samiul; Banik, Kalyan; Arif, Hossain

doi:10.1109/r10-htc.2018.8629845

Cited by 9 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bilen et al [5] proposed serveral regression model such as SMORegression (SMOReg), MultilaverPerceptron (MLP), and multivariate Linear Regression (Linear) to solve the businesss location selection problem. Widaningrum et al [6] proposed a combination of GIS and Support Vector Machine to predicts the class label to solve the location selection problem.Shihab et al [10] combine Support Vector Machine, Decision Tree and Logistic Regression for comparative analysis and searched for an algorithm that gives the best result for restaurant business location. Yang Yang et al [11] designed an automated web GIS application for evaluating potential hotel location.…”

Section: Related Workmentioning

confidence: 99%

“…Classification problem is a core problem of supervised learning, which learns a classification decision function or classification model (classifier) from data, makes output predictions for new input, and the output variable takes a finite number of discrete values [11]. In our proposed method, we use a binary classification method [10] to predict geographic locations to determine whether a geographic location is a good location for business establishments. The optimizer we use in solving this classification is Adam [12].…”

Section: Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Business Location Selection through Particle Swarm Optimization and Neural Network

Luo

Zhong

Liu

et al. 2023

2023 15th International Conference on Advanced Computational Intelligence (ICACI)

View full text Add to dashboard Cite

Location selection is an important part of running a business. A good business location can greatly increase customer flow, reduce operating costs, and increase business revenue. Therefore, it is necessary to select an appropriate location for business premises. In this research, we propose a method combining machine learning and particle swarm optimization for the business location selection. In the proposed method, we first apply the particle swarm algorithm to optimize the proportional coefficient of the influence of different surrounding commercial places on the site selection of the research site. Then we use a machine learning method to perform the binary classification on the sites to judge whether a geographic location is a good site selection point. The proposed method is compared with several common location selection methods such as random selection method and knearest neighbor method. The experimental results have validated the effectiveness of our proposed method for business location selection.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Selectionmentioning

confidence: 99%

Automatic Business Location Selection through Particle Swarm Optimization and Neural Network

Luo

Zhong

Liu

et al. 2023

2023 15th International Conference on Advanced Computational Intelligence (ICACI)

View full text Add to dashboard Cite

show abstract

“…They then did sentiment analysis on restaurant reviews, and using clustering algorithms, accuracy increased to 85%. Shihab et al (2018) proposed a viable place to start a restaurant business based on available data from Yelp, where 75 features were extracted for supervised machine learning. The model calculated the expected score a restaurant receive based on the characteristics the restaurant has.…”

Section: Literature Surveymentioning

confidence: 99%

Price Prediction Model for Restaurants In Istanbul By Using Machine Learning Algorithms

ŞAHİNBAŞ

2022

Ekonomi İşletme Ve Maliye Araştırmaları Dergisi

View full text Add to dashboard Cite

Today, companies have created new products based on data and accelerated the digitalization processes of businesses with the concept of data science. In this study, a price prediction model is proposed with machine learning algorithms by collecting the data of businesses in the food and beverage sector in Istanbul. In this study, different machine learning modeling algorithms such as XGBoost, Random Forest, Artificial Neural Network, K-Nearest Neighbor, Multi Linear Regression and CatBoost were used for restaurant price prediction. Classification algorithms were tested for price prediction, and as a result of the evaluation, it was observed that XGBoost algorithm achieve the highest performance with 0.023236 RMSE and 0.0005399 MSE error rates. By this study, business owners will be able to understand how new developments they will make in their businesses will benefit in terms of price and customer feedback. It will enable entrepreneurs to have information about what features a new business should have and the average price they will offer to their customers according to these features. In addition, entrepreneurs who want to open a restaurant will learn how much they should cost, provide price performance, and increase their profitability by selling more products because they will sell their products at affordable prices. Accurate pricing is one of the four important concepts of marketing. The company needs to make the right pricing in order to hold on and create customer loyalty.

show abstract

“…Nonetheless, the DPM proved inadequate for numerous instances of localizing images containing multiple objects. From a machine learning standpoint, Support Vector Machines (SVMs) and Bag of Words have been utilized in image analysis [10,71,72], yet their outcomes have been less than promising. However, more recently, deep learning has begun to eclipse other methodologies, garnering significant academic interest in various aerial-based object detection tasks [11,12].…”

Section: Introductionmentioning

confidence: 99%

Precise and Robust Sidewalk Detection: Leveraging Ensemble Learning to Surpass LLM Limitations in Urban Environments

Shihab,

Alvee,

Bhagat

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

This study aims to compare the effectiveness of a robust ensemble model with the state-of-the-art ONE-PEACE Large Language Model (LLM) for accurate detection of sidewalks. Accurate sidewalk detection is crucial in improving road safety and urban planning. The study evaluated the model’s performance on Cityscapes, Ade20k, and the Boston Dataset. The results showed that the ensemble model performed better than the individual models, achieving mean Intersection Over Union (mIOU) scores of 93.1%, 90.3%, and 90.6% on these datasets under ideal conditions. Additionally, the ensemble model maintained a consistent level of performance even in challenging conditions such as Salt-and-Pepper and Speckle noise, with only a gradual decrease in efficiency observed. On the other hand, the ONE-PEACE LLM performed slightly better than the ensemble model in ideal scenarios but experienced a significant decline in performance under noisy conditions. These findings demonstrate the robustness and reliability of the ensemble model, making it a valuable asset for improving urban infrastructure related to road safety and curb space management. This study contributes positively to the broader context of urban health and mobility.

show abstract

A Machine Learning Approach to Suggest Ideal Geographical Location for New Restaurant Establishment

Cited by 9 publications

References 8 publications

Automatic Business Location Selection through Particle Swarm Optimization and Neural Network

Automatic Business Location Selection through Particle Swarm Optimization and Neural Network

Price Prediction Model for Restaurants In Istanbul By Using Machine Learning Algorithms

Precise and Robust Sidewalk Detection: Leveraging Ensemble Learning to Surpass LLM Limitations in Urban Environments

Contact Info

Product

Resources

About