Large AI systems and foundation models rely on continuous and consistent numeric data. In real life, missing values
are common in the time-series data because of gaps in reporting, measurement failures, or archival errors. If these are not han
dled well, they have the potential to alter the distribution of the data, bias learning, and hurt model performance. In this paper,
we presented a simple, intuitive, deterministic interpolation approach to fill gaps in long-term numeric time series. Unlike the
imputation approach, which has latent, black-box-type imputation, this uses a step-by-step mathematical process; as such, trac
ing and verifying statistically are easily achieved. We tested the method on a historical Standard Yield (SY) dataset from 1950
2009, to which we artificially introduce missing values and then reconstruct. We utilize a comprehensive set of statistical tests
for the descriptive statistics, variance and covariance comparisons, and one-way ANOVA to demonstrate that in average value,
the dispersion, and the time-varying process, the original data is closely matched with the recovered series. This demonstrates
that classic, interpretable reconstruction methods are still relevant in a modern AI pipeline, during the preprocessing stage of
foundation models, which demands data quality, stability, and explain ability.
[1] OECD. (2021). Artificial intelligence, big data and the future of skills. OECD Publishing.
https://doi.org/10.1787/9789264314626-en
[2] Stanford University. (2022). Artificial Intelligence Index Report 2022. Human-Centered AI Institute, Stanford University.
[3] Brynjolfsson, E., & McAfee, A. (2017). The second machine age: Work, progress, and prosperity in a time of brilliant
technologies. W. W. Norton & Company.
[4] Pandya, D.D., Jadeja, A., Trivedi, S., Patel, P.A., Tamhankar, I., Dhanesha, P.S. (2026). Internet of Things (IoT)’s Trans
formative Power Enhancing Wireless Networks and Sensing. In: Rathore, V.S., Piuri, V., Babo, R., Karthik, S. (eds) Uni
versal Threats in Expert Applications and Solutions. UNI-TEAS 2025
[5] Dr. DarshanabenDipakkumarPandya, Dr. AbhijeetsinhJadeja, Dr. SheshangDegadwala, " An Applied Variation Anomaly
Technique for Detection of Irregular Values in Data Mining, IInternational Journal of Scientific Research in Computer
Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 8, Issue 2, pp.143-148,
March-April-2022. Available at doi :https://doi.org/10.32628/CSEIT228228.
[6] Gora KanijfatmaMaisurali, HabibaVajiraliMomin, Dr. DarshanabenDipakkumarPandya, Dr. AbhijeetsinhJadeja, " Smart
Cook : An AI and Machine Learning Powered Culinary, IInternational Journal of Scientific Research in Computer Sci
ence, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 10, Issue 1, pp.55-59, January
February-2024.
[7] YashNaraynbhai Patel, Dr. DarshanabenDipakkumarPandya, Dr. AbhijeetsinhJadeja, " An Influence of Ethical Hacking in
Civilization , International Journal of Scientific Research in Science and Technology(IJSRST), Online ISSN : 2395-602X,
Print ISSN : 2395-6011, Volume 10, Issue 1, pp.195-200, January-February-2023. Available at doi
: https://doi.org/10.32628/IJSRST2310119
[8] Pandya, D., Jadeja, A., Bhuptani, M., Patel, V., Mehta, K., &Brahmbhatt, D. (2024). Machine Learning: Enhancing Cyber
security through Attack Detection and Identification. ITM Web of Conferences, 65, 03010.
https://doi.org/10.1051/itmconf/20246503010
[9]Pandya, D., Jadeja, A., Khan, M.A., Trivedi, S.B., Ramnath, M.A., Satish, B.P. (2024). Significance of Sentiment Analysis
with Text-Based Mining Approach. In: Rathore, V.S., Piuri, V., Babo, R., Tiwari, V. (eds) Emerging Trends in Expert Ap
plications and Security. ICE-TEAS 2024. Lecture Notes in Networks and Systems, vol 1037. Springer, Singapore.
https://doi.org/10.1007/978-981-97-3991-2_27
[10] HeemaPatadiya, Akshay Patel, FalguniRahevar, and Dr. DarshanabenDipakkumarPandya, “Revolutionizing Banking In
dustry : The Role of Fintech in Modern Banking Industry”, Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol, vol. 11, no. 4,
pp. 20–25, Jul. 2025, doi: 10.32628/CSEIT25113448.
