Submit or Track your Manuscript LOG-IN

Estimation of Honey Production in Beekeeping Enterprises from Eastern Part of Turkey through Some Data Mining Algorithms

Estimation of Honey Production in Beekeeping Enterprises from Eastern Part of Turkey through Some Data Mining Algorithms

Adem Aksoy1, Yakup Erdal Ertürk2, Selim Erdoğan3, Ecevit Eyduran3 andMohammad Masood Tariq4,*

1Department of Agricultural Economics, Agricultural Faculty, Atatürk University, Erzurum, Turkey
2Department of Agricultural Economics, Agricultural Faculty, Igdir University, Igdir, Turkey
3Department of Business, Faculty of Economics and Business Administration, Igdir University, Igdir, Turkey
4Centre of Advanced Studies in Vaccinology and Biotechnology, University of Balochistan, Quetta, Pakistan

*      Corresponding author: tariqkianiraja@hotmail.com

 

ABSTRACT

The aim of this study was to develop a honey production model for 180 beekeeping enterprises at Agri, Kars and Erzurum provinces of Turkey and to identify factors affecting honey production through CART, CHAID and MARS data mining algorithms, which are more flexible compared to classical approaches. Several potential predictors in the survey were age of enterprise, province of enterprise (Agri, Kars and Erzurum), educational level, membership status of enterprise to an association of beekeepers (member and nonmember), other activities except for beekeeping (yes and no), number of full beehives, bee race (Caucasian, Carniolan, Italian and Crossbred), and frequency of changing queen bee. MARS outperformed multiple linear regression, and CART in honey yield per hive. No solution for CHAID was generated. In CART algorithm, the highest honey yield per hive (51.250 kg) was obtained from the 33.5 or younger enterprises that performed only beekeeping activity. The four most influential predictors in the MARS were age of enterprise (100%), number of full beehives (100%), other races (97%), and other works except for beekeeping (90%). The best performance order was MARS (r=0.920) > CART (r=0.619) > multiple linear regression (r=0.286), which indicated that MARS outperformed other approaches. MARS reflected that the main and interaction effects of socioeconomic (age of enterprise, province of enterprise, educational level, membership status, other works except for beekeeping and number of full beehives), biological predictors (bee race and frequency of changing queen bee) affected honey yield per hive. As a result, it is recommended that the effect of socioeconomic and biological predictors on the yield should be assessed jointly for further studies.
 

To share on other social networks, click on P-share. What are these?

Pakistan Journal of Zoology

December

Vol. 50, Iss. 6, Pages 1999-2398

Featuring

Click here for more

Subscribe Today

Receive free updates on new articles, opportunities and benefits


Subscribe Unsubscribe